© 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 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. 929
    Prev
    Next
    INDEX
    Explanations

    text related to programming, specifically code snippets and programming instructions

    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
    106
    +0.12
    0.5%
    434
    +0.11
    0.4%
    653
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.02
    692
    +0.11
    0.02
    453
    +0.11
    0.02
    Negative Logits
    soDeliveryDate
    -0.95
    borough
    -0.90
    emouth
    -0.81
     Oaks
    -0.81
    INTON
    -0.78
     Skydragon
    -0.77
    arten
    -0.76
    ween
    -0.74
    artz
    -0.74
    aimon
    -0.72
    POSITIVE LOGITS
    uren
    0.79
     Safe
    0.75
     IG
    0.75
     Boolean
    0.73
     BRA
    0.73
     Topic
    0.72
     Alloy
    0.71
     GER
    0.70
     Beautiful
    0.70
     Bloody
    0.69
    Activations Density 0.061%

    No Known Activations