© 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 Local
    9. 6-RES_SCL-AJT
    11. 35984
    Prev
    Next
    INDEX
    Explanations

    locations or names of states

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.25
    1.1%
    288
    +0.16
    0.7%
    643
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.25
    0.18
    31
    +0.16
    0.13
    659
    +0.12
    0.11
    Negative Logits
    htar
    -0.83
    deck
    -0.82
    henko
    -0.81
    fen
    -0.78
    colo
    -0.78
    BOOK
    -0.76
    byn
    -0.76
    chel
    -0.75
    fare
    -0.75
    pter
    -0.74
    POSITIVE LOGITS
     Springs
    1.16
     State
    1.11
     Gov
    1.03
     Legislature
    0.98
     Rapids
    0.95
     Governor
    0.95
     Attorney
    0.94
     Department
    0.94
     Railroad
    0.93
     Tech
    0.92
    Activations Density 6.627%

    No Known Activations