© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    information related to events, ticket sales, and specific locations

    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
    288
    +0.21
    0.7%
    121
    +0.15
    0.5%
    437
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.06
    575
    +0.15
    0.05
    343
    +0.14
    0.04
    Negative Logits
     territ
    -0.98
    phrine
    -0.96
    sembly
    -0.96
    rike
    -0.94
    issance
    -0.94
    aukee
    -0.93
    naissance
    -0.93
    ossus
    -0.92
     nomine
    -0.90
     teamwork
    -0.89
    POSITIVE LOGITS
     Tickets
    1.44
     tickets
    1.37
    Tickets
    1.37
     holders
    1.33
    ticket
    1.20
     Ticket
    1.16
    holders
    1.15
     ticket
    1.13
     holder
    1.07
    posts
    1.02
    Activations Density 0.637%

    No Known Activations