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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34444
    Prev
    Next
    INDEX
    Explanations

    dialogue and descriptions of character actions in 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
    218
    +0.15
    0.6%
    447
    +0.14
    0.6%
    762
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.38
    526
    +0.14
    -0.12
    762
    +0.12
    0.26
    Negative Logits
    busters
    -0.92
    Critics
    -0.88
     Critics
    -0.86
    SPONSORED
    -0.82
     domestically
    -0.81
    cki
    -0.80
    govtrack
    -0.80
    osponsors
    -0.79
    buster
    -0.79
    ocumented
    -0.78
    POSITIVE LOGITS
     Jaune
    1.05
     Arkham
    1.00
     Weasley
    0.99
     Pyrrha
    0.97
     crimson
    0.95
     faint
    0.94
     runes
    0.91
     Voldemort
    0.91
     potions
    0.90
     Naruto
    0.89
    Activations Density 23.468%

    No Known Activations