© 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. 341
    Prev
    Next
    INDEX
    Explanations

    reasons or justifications for a situation or phenomenon

    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
    195
    +0.22
    0.7%
    679
    +0.19
    0.6%
    235
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.22
    0.04
    239
    +0.19
    0.04
    679
    +0.14
    0.06
    Negative Logits
    illet
    -1.22
    jet
    -1.06
    engeance
    -1.03
    estial
    -1.00
    luster
    -0.99
    emp
    -0.93
    ammy
    -0.93
    nir
    -0.91
    ategory
    -0.91
    mire
    -0.91
    POSITIVE LOGITS
     why
    1.45
     WHY
    1.31
    udic
    1.09
    why
    1.08
    ĸļ
    1.07
     how
    1.01
    ance
    1.01
    cases
    0.99
    ¿½
    0.98
     explanations
    0.97
    Activations Density 0.888%

    No Known Activations