© 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 EvalsExportsinterp-engineNEWAPI 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. 7811
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and championships

    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
    746
    +0.11
    0.4%
    359
    +0.11
    0.4%
    725
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    326
    +0.11
    0.06
    359
    +0.11
    0.04
    Negative Logits
    rawdownloadcloneembedreportprint
    -1.08
    dal
    -0.99
    cair
    -0.96
    alos
    -0.93
    draw
    -0.92
    ivan
    -0.92
    lasses
    -0.89
    patrick
    -0.88
    gers
    -0.87
    urn
    -0.87
    POSITIVE LOGITS
    ĸļ
    1.05
     EDITION
    0.92
     disadvant
    0.89
     unden
    0.89
    ERE
    0.84
    ZI
    0.83
     challeng
    0.83
     oun
    0.81
    ¬¼
    0.81
    ERT
    0.80
    Activations Density 0.553%

    No Known Activations