© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hack"

    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
    204
    +0.09
    0.3%
    50
    +0.08
    0.3%
    757
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1293
    +0.09
    0.03
    631
    +0.08
    0.02
    1343
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.92
     AssemblyProduct
    -0.74
    ുറ
    -0.73
    FieldBuilder
    -0.69
    PTI
    -0.69
    ്ല
    -0.69
    public
    -0.66
    PROTOBUF
    -0.64
    <tr>
    -0.63
    else
    -0.63
    POSITIVE LOGITS
     affor
    1.83
     accla
    1.77
     increa
    1.74
     maneu
    1.73
     reluct
    1.70
     scrat
    1.70
     impra
    1.65
     hairc
    1.64
     suscep
    1.61
     depic
    1.57
    Activations Density 0.181%

    No Known Activations