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

    Neuronpedia

    Jacobian LensNEW
    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. 12254
    Prev
    Next
    INDEX
    Explanations

    references to specific names or keywords, including those related to current events or individuals

    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
    526
    +0.13
    0.6%
    575
    +0.12
    0.6%
    0
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.07
    288
    +0.12
    0.08
    659
    +0.11
    0.05
    Negative Logits
    ITNESS
    -0.74
    Austral
    -0.64
    ECK
    -0.63
    CRIP
    -0.63
    ittee
    -0.63
    IELD
    -0.62
     Samar
    -0.61
    Giving
    -0.60
    onso
    -0.59
    VERTISEMENT
    -0.59
    POSITIVE LOGITS
    rosse
    0.99
    kered
    0.94
    imar
    0.74
    imore
    0.72
    mo
    0.70
    atures
    0.70
    umber
    0.70
    waukee
    0.69
    bourg
    0.69
    ourses
    0.66
    Activations Density 0.600%

    No Known Activations