© 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. 32270
    Prev
    Next
    INDEX
    Explanations

    details about personal experiences in a story or narrative context

    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%
    511
    +0.12
    0.5%
    641
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.38
    375
    +0.12
    0.04
    393
    +0.11
    0.36
    Negative Logits
    ulty
    -0.85
    alion
    -0.79
    aptic
    -0.79
    ropy
    -0.79
    finished
    -0.79
    inctions
    -0.78
    iqueness
    -0.77
    ioch
    -0.74
    ollar
    -0.71
    imilation
    -0.69
    POSITIVE LOGITS
     airplanes
    0.87
     whirlwind
    0.81
    è¦ļéĨĴ
    0.79
     Tours
    0.76
     Disneyland
    0.75
     continents
    0.74
     fumes
    0.74
     simulator
    0.72
     abroad
    0.72
     vans
    0.72
    Activations Density 22.696%

    No Known Activations