© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8511
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions, particularly informed decisions based on information and optimization strategies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.19
    0.6%
    575
    +0.15
    0.5%
    540
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.19
    0.13
    575
    +0.15
    0.12
    679
    +0.14
    0.12
    Negative Logits
    riot
    -1.03
    bing
    -1.02
    drops
    -0.95
    Jet
    -0.94
    awar
    -0.91
     maiden
    -0.90
    ench
    -0.90
    ARS
    -0.89
    Anti
    -0.88
    nery
    -0.87
    POSITIVE LOGITS
     decisions
    1.33
    omething
    1.19
    eering
    1.04
     regarding
    0.97
     choices
    0.96
     differently
    0.91
     parameters
    0.90
     levers
    0.90
     assumptions
    0.89
     accordingly
    0.89
    Activations Density 1.728%

    No Known Activations