Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13479
    Prev
    Next
    INDEX
    Explanations

    narrative elements and storytelling techniques

    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
    +0.24
    1.2%
    288
    +0.15
    0.7%
    339
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.24
    0.14
    77
    +0.15
    0.07
    512
    +0.12
    0.07
    Negative Logits
    ertodd
    -0.96
    unte
    -0.85
    ateurs
    -0.78
    sterdam
    -0.76
    achev
    -0.75
    enhagen
    -0.73
    gans
    -0.72
    ikarp
    -0.69
    ldon
    -0.68
    untary
    -0.67
    POSITIVE LOGITS
     arcs
    0.78
     narratives
    0.75
     narrative
    0.70
     unfolds
    0.68
    telling
    0.68
     driven
    0.66
     synopsis
    0.65
    istically
    0.65
     disson
    0.64
     storylines
    0.63
    Activations Density 7.416%

    No Known Activations