© 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. 33323
    Prev
    Next
    INDEX
    Explanations

    brief phrases where a narrative or story unfolds

    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
    67
    +0.17
    0.7%
    320
    +0.15
    0.7%
    745
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    -0.01
    373
    +0.15
    -0.15
    406
    +0.12
    0.11
    Negative Logits
     Annotations
    -0.87
    代
    -0.81
     Triangle
    -0.77
    REDACTED
    -0.74
    DERR
    -0.70
     Expend
    -0.68
     Leilan
    -0.68
     Airbus
    -0.68
     Odyssey
    -0.68
     gems
    -0.67
    POSITIVE LOGITS
    gged
    1.33
    gging
    1.31
    cks
    1.18
    pload
    1.14
    pper
    1.09
    vered
    1.04
    opy
    1.03
    asant
    1.03
    ggle
    1.02
    veland
    1.00
    Activations Density 6.679%

    No Known Activations