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

    Neuronpedia

    Jacobian LensNEW
    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. 33443
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming, specifically methods, fields, and classes in code snippets

    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
    326
    +0.12
    0.5%
    410
    +0.12
    0.5%
    275
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.20
    373
    +0.12
    -0.16
    615
    +0.11
    0.06
    Negative Logits
    anders
    -0.79
     condos
    -0.77
    ciation
    -0.76
    yss
    -0.74
     juices
    -0.73
    ges
    -0.71
    esville
    -0.69
    ducers
    -0.67
    endale
    -0.66
    SEA
    -0.65
    POSITIVE LOGITS
    ptr
    0.82
     __
    0.80
     setup
    0.73
    Setup
    0.72
     Init
    0.71
    Ptr
    0.70
     func
    0.70
     Setup
    0.68
     dun
    0.68
     guiIcon
    0.67
    Activations Density 6.729%

    No Known Activations