© 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. 12368
    Prev
    Next
    INDEX
    Explanations

    text related to technical programming concepts and coding 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
    393
    +0.22
    0.9%
    679
    +0.14
    0.6%
    267
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.22
    0.09
    208
    +0.14
    0.09
    233
    +0.13
    0.08
    Negative Logits
    ãģ®
    -0.84
    \":
    -0.81
    heard
    -0.78
    abilities
    -0.77
     Purg
    -0.71
    guard
    -0.71
    shore
    -0.71
    stre
    -0.70
    abe
    -0.69
     segment
    -0.67
    POSITIVE LOGITS
    tons
    1.85
     alas
    1.20
    tery
    1.18
     nevertheless
    1.06
    ts
    1.03
     fortunately
    1.01
     luckily
    1.01
    chery
    0.98
     whereas
    0.97
    gans
    0.94
    Activations Density 1.396%

    No Known Activations