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. 34159
    Prev
    Next
    INDEX
    Explanations

    text related to items for purchase or sale

    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
    480
    +0.53
    3.1%
    447
    +0.09
    0.5%
    591
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.06
    266
    +0.09
    0.53
    138
    +0.08
    0.17
    Negative Logits
     guiName
    -0.74
    etheless
    -0.56
    wcs
    -0.44
    ":[{"
    -0.43
    foreseen
    -0.42
     showc
    -0.40
    ADVERTISEMENT
    -0.39
     withd
    -0.38
    gencies
    -0.38
    answered
    -0.38
    POSITIVE LOGITS
    )
    1.42
    ?)
    1.42
    )."
    1.39
    )"
    1.38
    ),"
    1.35
    !)
    1.35
    ?).
    1.34
    ),
    1.34
    ?),
    1.33
    )?
    1.33
    Activations Density 36.984%

    No Known Activations