© 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. 8589
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes related to software or technology

    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
    270
    +0.16
    0.6%
    326
    +0.15
    0.6%
    274
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.07
    288
    +0.15
    0.07
    659
    +0.14
    0.05
    Negative Logits
    naire
    -0.95
    ships
    -0.94
    hower
    -0.93
    bart
    -0.88
    hang
    -0.88
    ysis
    -0.88
    naires
    -0.87
     quickest
    -0.82
    hof
    -0.82
    tons
    -0.82
    POSITIVE LOGITS
    VE
    1.38
    BILITIES
    1.33
    ULT
    1.20
    plings
    1.16
    ven
    1.14
    FE
    1.12
    BILITY
    1.05
    ccess
    1.03
    VER
    0.99
    UD
    0.98
    Activations Density 0.769%

    No Known Activations