© 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. 45896
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and data analysis

    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
    264
    +0.14
    0.6%
    447
    +0.14
    0.6%
    278
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.14
    0.09
    81
    +0.14
    0.12
    742
    +0.11
    0.09
    Negative Logits
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.82
    ________________________________
    -0.72
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.69
    .?
    -0.68
    ————————
    -0.68
    ~~~~
    -0.67
     ........
    -0.66
    Īè
    -0.66
    >:
    -0.65
    ARY
    -0.65
    POSITIVE LOGITS
    luaj
    0.80
     istg
    0.67
    foundland
    0.67
     Strait
    0.65
    duction
    0.63
     coasts
    0.62
    enture
    0.61
    soDeliveryDate
    0.61
    vana
    0.61
    ovo
    0.60
    Activations Density 10.918%

    No Known Activations