© 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. 36599
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations related to Canada

    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
    +0.09
    0.5%
    46
    +0.08
    0.4%
    521
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.39
    6
    +0.08
    0.27
    283
    +0.08
    0.06
    Negative Logits
     guiActiveUn
    -0.62
    ngth
    -0.61
    igers
    -0.58
    igraph
    -0.57
    keleton
    -0.57
    osures
    -0.56
    itia
    -0.55
     reven
    -0.53
     reflection
    -0.52
    ertation
    -0.52
    POSITIVE LOGITS
    lehem
    0.82
    pillar
    0.66
    mingham
    0.65
    levard
    0.62
    dylib
    0.59
     Aires
    0.59
    hatt
    0.58
    aughs
    0.57
     Mellon
    0.57
    burning
    0.56
    Activations Density 13.905%

    No Known Activations