© 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 EvalsExportsinterp-engineNEWAPI 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. 36334
    Prev
    Next
    INDEX
    Explanations

    sports-related phrases, particularly related to women's sports

    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
    +0.16
    0.7%
    664
    +0.11
    0.5%
    556
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.16
    0.17
    193
    +0.11
    0.16
    48
    +0.10
    0.15
    Negative Logits
    æ©Ł
    -0.81
    quickShipAvailable
    -0.80
    hess
    -0.67
    OVER
    -0.65
    changes
    -0.64
    Priv
    -0.63
    Reviewed
    -0.63
    ozy
    -0.63
    OSH
    -0.62
    PN
    -0.60
    POSITIVE LOGITS
    selves
    0.81
    idia
    0.79
    hood
    0.79
    cience
    0.77
    wered
    0.74
    achusetts
    0.71
    atisf
    0.71
    istance
    0.66
    lander
    0.66
     alike
    0.66
    Activations Density 8.283%

    No Known Activations