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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13467
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific research and experiments

    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
    706
    +0.16
    0.6%
    1
    +0.12
    0.5%
    315
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.16
    575
    +0.12
    0.11
    326
    +0.12
    0.11
    Negative Logits
    iquette
    -0.86
    regate
    -0.85
     respawn
    -0.85
    osta
    -0.84
    endi
    -0.83
     veter
    -0.82
    opa
    -0.81
    panic
    -0.81
    ido
    -0.79
     lockout
    -0.78
    POSITIVE LOGITS
     applications
    1.09
     application
    0.98
     Application
    0.90
     Applications
    0.89
    utics
    0.86
    RNA
    0.86
     Letters
    0.85
     nanop
    0.85
     solutions
    0.83
    Applications
    0.81
    Activations Density 1.991%

    No Known Activations