© 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. 33853
    Prev
    Next
    INDEX
    Explanations

    details related to plotlines, characters, and relationships in a 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
    +0.26
    1.2%
    476
    +0.11
    0.5%
    610
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.26
    0.08
    766
    +0.11
    0.09
    427
    +0.10
    0.08
    Negative Logits
    ertodd
    -0.83
    cipled
    -0.78
    usra
    -0.75
    ollah
    -0.74
    reprene
    -0.73
    ulic
    -0.73
    yden
    -0.73
    regulated
    -0.72
    ustainable
    -0.71
    lah
    -0.71
    POSITIVE LOGITS
     Characters
    1.32
    Characters
    1.21
     characters
    1.20
     protagonist
    1.19
     cinematic
    1.16
     storyline
    1.12
     flashbacks
    1.11
     narrator
    1.06
     Animation
    1.06
    episode
    1.04
    Activations Density 32.287%

    No Known Activations