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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12799
    Prev
    Next
    INDEX
    Explanations

    historical references and academic citations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
    447
    +0.17
    1.0%
    659
    +0.11
    0.7%
    406
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.17
    0.19
    326
    +0.11
    0.44
    284
    +0.10
    0.17
    Negative Logits
     forging
    -0.53
     forged
    -0.50
     fictitious
    -0.50
     whine
    -0.49
     scratch
    -0.49
     millennial
    -0.49
     happiest
    -0.49
     braking
    -0.49
     metaphors
    -0.48
     antis
    -0.48
    POSITIVE LOGITS
    cia
    0.85
    je
    0.77
    ansky
    0.75
    anie
    0.74
    zynski
    0.74
    aru
    0.73
    ko
    0.73
    jen
    0.72
    unda
    0.72
    lette
    0.71
    Activations Density 32.211%

    No Known Activations