© 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
    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. 40433
    Prev
    Next
    INDEX
    Explanations

    references to coding frameworks or platforms

    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
    218
    +0.17
    0.8%
    167
    +0.15
    0.7%
    343
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.23
    326
    +0.15
    0.20
    343
    +0.13
    0.10
    Negative Logits
     circuit
    -0.78
    iquid
    -0.73
    ãģĨ
    -0.72
     Haram
    -0.71
     Trip
    -0.71
    Charge
    -0.67
    REDACTED
    -0.67
     Ops
    -0.66
    onomy
    -0.65
     Alibaba
    -0.65
    POSITIVE LOGITS
    erate
    1.39
    pton
    1.24
    eworks
    1.23
    ingham
    1.16
    eenth
    1.01
    ership
    0.98
    esty
    0.94
    ance
    0.93
    eline
    0.86
    raped
    0.85
    Activations Density 6.166%

    No Known Activations