© 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. 13355
    Prev
    Next
    INDEX
    Explanations

    various forms of contractions, specifically " 've" and " 's"

    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
    566
    +0.17
    0.6%
    173
    +0.13
    0.4%
    393
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.17
    0.09
    354
    +0.13
    0.06
    173
    +0.13
    0.06
    Negative Logits
    eem
    -0.93
    quote
    -0.86
    imately
    -0.83
    ancing
    -0.82
    aphael
    -0.81
    izes
    -0.81
    Subject
    -0.80
    omial
    -0.79
    Reviewer
    -0.79
    oubt
    -0.79
    POSITIVE LOGITS
     been
    2.02
    been
    1.94
     gotta
    1.93
     gotten
    1.71
     got
    1.68
     Been
    1.63
     gone
    1.41
    gotten
    1.38
     done
    1.31
     undergone
    1.29
    Activations Density 0.988%

    No Known Activations