© 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. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1791
    Prev
    Next
    INDEX
    Explanations

    mentions of items related to clothing, specifically focusing on hoods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1350
    +0.09
    0.3%
    68
    +0.09
    0.3%
    1942
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.09
    0.02
    861
    +0.09
    0.02
    1971
    +0.09
    0.02
    Negative Logits
    bibnamefont
    -0.86
    text
    -0.64
     present
    -0.64
    /**
    -0.63
    int
    -0.62
    多
    -0.61
    .
    -0.61
    ع
    -0.61
    char
    -0.59
    /**
    -0.59
    POSITIVE LOGITS
     hood
    2.92
    Hood
    2.65
     Hood
    2.62
     hoods
    2.61
    hood
    2.19
    HOOD
    2.04
     franz
    1.73
     emphat
    1.71
     wien
    1.70
     effe
    1.65
    Activations Density 0.213%

    No Known Activations