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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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 Local
    5. 6-RES_SCL-AJT
    6. 45079
    Prev
    Next
    INDEX
    Explanations

    details about membership offers and benefits

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.15
    1.3%
    481
    +0.13
    1.2%
    373
    +0.08
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    -0.30
    481
    +0.13
    0.31
    620
    +0.08
    -0.04
    Negative Logits
     Chiefs
    -0.28
    hatt
    -0.27
    cro
    -0.27
     spoilers
    -0.27
     setbacks
    -0.27
     Lauder
    -0.26
    rene
    -0.26
    urances
    -0.25
     setback
    -0.25
    awn
    -0.25
    POSITIVE LOGITS
     Cosponsors
    0.33
    anooga
    0.32
     --------------------------------
    0.31
     FG
    0.30
     --------------------
    0.30
    MSN
    0.30
    razil
    0.29
     LTD
    0.29
    stros
    0.28
     ----------------
    0.28
    Activations Density 19.946%

    No Known Activations