© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 45902
    Prev
    Next
    INDEX
    Explanations

    Descriptions of events happening in a specific location

    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
    +0.54
    5.4%
    447
    +0.28
    2.8%
    195
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.54
    0.06
    266
    +0.28
    0.61
    276
    +0.06
    0.35
    Negative Logits
    .</
    -0.33
    $.
    -0.32
     thereof
    -0.32
     ..."
    -0.31
    ]."
    -0.28
    Recomm
    -0.28
    }.
    -0.28
    )."
    -0.28
    ··
    -0.28
    .''.
    -0.28
    POSITIVE LOGITS
     meanwhile
    0.45
     however
    0.37
     Edit
    0.28
    surprisingly
    0.27
     moreover
    0.27
     irony
    0.26
    nce
    0.26
     therefore
    0.26
    endum
    0.26
     Variant
    0.24
    Activations Density 40.731%

    No Known Activations