© 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. 7668
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations, specifically focusing on Hawaii

    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
    269
    +0.15
    0.5%
    253
    +0.13
    0.5%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.09
    288
    +0.13
    0.09
    326
    +0.13
    0.08
    Negative Logits
    parts
    -1.06
    ures
    -0.97
    rations
    -0.97
    Interstitial
    -0.92
    urgical
    -0.90
    byn
    -0.89
    oration
    -0.87
    skirts
    -0.84
     Notting
    -0.83
    */(
    -0.82
    POSITIVE LOGITS
    aii
    1.61
    velength
    1.20
     Islands
    1.09
     Hawai
    1.07
    Ń·
    1.07
    awks
    1.05
    awei
    1.02
    ulu
    0.98
     Honolulu
    0.95
    renheit
    0.95
    Activations Density 1.079%

    No Known Activations