© 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. 11943
    Prev
    Next
    INDEX
    Explanations

    references to bus-related activities and 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
    +0.23
    0.8%
    484
    +0.20
    0.7%
    417
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.08
    343
    +0.20
    0.06
    326
    +0.19
    0.06
    Negative Logits
    sson
    -1.07
     marrow
    -1.02
    aneous
    -0.98
     Martial
    -0.97
     Centauri
    -0.95
    nesota
    -0.93
    vironment
    -0.87
    ixture
    -0.85
    aughters
    -0.85
    ffen
    -0.82
    POSITIVE LOGITS
    loads
    1.62
    load
    1.41
    boys
    1.38
    hel
    1.36
    INESS
    1.33
    boy
    1.18
    kers
    1.10
    dump
    1.08
    ilet
    1.08
    hell
    1.06
    Activations Density 0.992%

    No Known Activations