Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 615
    Prev
    Next
    INDEX
    Explanations

    statements discussing reasons or justifications

    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
    +0.21
    0.7%
    65
    +0.19
    0.6%
    155
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.21
    0.04
    155
    +0.19
    0.04
    513
    +0.17
    0.03
    Negative Logits
    lich
    -1.02
    rop
    -1.00
    ergy
    -0.99
    pit
    -0.96
    mage
    -0.96
     skelet
    -0.92
    ty
    -0.90
     Devils
    -0.89
    erion
    -0.88
    aith
    -0.88
    POSITIVE LOGITS
     why
    1.24
    soever
    1.08
    forward
    1.00
    terday
    0.99
    nces
    0.99
    ioned
    0.93
    ¿½
    0.90
    quickShipAvailable
    0.89
    alde
    0.88
    HAEL
    0.86
    Activations Density 0.213%

    No Known Activations