© 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. 39992
    Prev
    Next
    INDEX
    Explanations

    references to physical spaces and the organization of items within those spaces

    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
    +0.28
    1.1%
    288
    +0.16
    0.7%
    578
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.28
    0.04
    459
    +0.16
    0.09
    726
    +0.14
    0.06
    Negative Logits
    ctive
    -0.82
    usted
    -0.82
    venge
    -0.81
    iamond
    -0.80
    otine
    -0.75
    ongyang
    -0.73
     Simpson
    -0.70
    issance
    -0.69
     vengeance
    -0.69
    kai
    -0.68
    POSITIVE LOGITS
     spaces
    1.07
     space
    1.04
     Layout
    0.92
     constraints
    0.90
     Spaces
    0.88
    bars
    0.86
     habitats
    0.86
    bar
    0.86
     occupied
    0.86
     shuttle
    0.85
    Activations Density 7.093%

    No Known Activations