© 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. 45727
    Prev
    Next
    INDEX
    Explanations

    uppercase words, potentially related to titles and headings

    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
    718
    +0.11
    0.6%
    238
    +0.10
    0.5%
    565
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.11
    0.07
    308
    +0.10
    0.04
    300
    +0.10
    0.11
    Negative Logits
    ragon
    -0.76
     Preferred
    -0.61
     Gauntlet
    -0.57
    Tags
    -0.57
     Agility
    -0.56
     Solitaire
    -0.55
     Modes
    -0.53
    Rust
    -0.53
    Compan
    -0.52
     Noir
    -0.52
    POSITIVE LOGITS
    ITY
    0.91
    NA
    0.86
    ISE
    0.86
    KE
    0.85
    OUS
    0.80
    PLIC
    0.79
    isine
    0.78
    ITS
    0.77
    DE
    0.77
    pport
    0.77
    Activations Density 4.213%

    No Known Activations