© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    scientific terms and citations

    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
    68
    +0.06
    0.5%
    408
    +0.06
    0.5%
    627
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.06
    0.27
    640
    +0.06
    0.22
    283
    +0.06
    0.01
    Negative Logits
    winter
    -0.37
     footnote
    -0.36
    minimum
    -0.35
    REF
    -0.35
    APTER
    -0.35
     negotiate
    -0.35
    ACA
    -0.35
    vertisement
    -0.35
     fortunately
    -0.35
    note
    -0.35
    POSITIVE LOGITS
     MPG
    0.44
     Sty
    0.42
     Jr
    0.40
     Jo
    0.39
     Rye
    0.39
     Hait
    0.38
     Tone
    0.38
     Aless
    0.38
     Md
    0.37
     Bened
    0.37
    Activations Density 9.929%

    No Known Activations