© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14344
    Prev
    Next
    INDEX
    Explanations

    references to a specific character or event in a particular context, such as a movie or historical era

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.33
    1.1%
    385
    +0.18
    0.6%
    167
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.33
    0.23
    393
    +0.18
    0.23
    362
    +0.15
    0.21
    Negative Logits
    thood
    -1.02
    advertising
    -0.91
    afe
    -0.87
    aunder
    -0.85
    arate
    -0.85
     Gerard
    -0.80
     Paulo
    -0.80
    vine
    -0.80
    ivably
    -0.79
     Africa
    -0.78
    POSITIVE LOGITS
    ses
    1.31
     hardest
    1.19
     longest
    1.13
     entire
    1.13
     quickest
    1.13
     brightest
    1.11
     way
    1.11
     same
    1.09
     whole
    1.09
     hottest
    1.07
    Activations Density 4.837%

    No Known Activations