© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39607
    Prev
    Next
    INDEX
    Explanations

    references to different types of scenes, possibly focusing on events or locations within a story

    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
    +0.28
    1.4%
    709
    +0.13
    0.6%
    561
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.28
    0.25
    362
    +0.13
    0.17
    393
    +0.09
    0.29
    Negative Logits
    thood
    -0.84
     Seym
    -0.81
    achev
    -0.78
    dp
    -0.74
    icrobial
    -0.73
    berman
    -0.73
    secut
    -0.73
    reditary
    -0.68
    dinand
    -0.68
    atever
    -0.67
    POSITIVE LOGITS
     Scene
    0.82
    Dialogue
    0.82
    Capture
    0.81
     Scenes
    0.77
     scenes
    0.75
     involving
    0.73
     unfolding
    0.71
    scene
    0.71
     Presence
    0.65
    LINE
    0.64
    Activations Density 12.643%

    No Known Activations