© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    names related to a specific entity, likely "Bradley"

    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
    1387
    +0.13
    0.4%
    1708
    +0.11
    0.4%
    555
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.13
    0.03
    690
    +0.11
    0.04
    438
    +0.10
    0.03
    Negative Logits
    <bos>
    -0.81
     препратки
    -0.62
     thất
    -0.60
    ീ
    -0.58
     parseFrom
    -0.58
    mergeFrom
    -0.57
    น์
    -0.57
     es
    -0.57
    Oneof
    -0.57
     der
    -0.57
    POSITIVE LOGITS
     Traité
    1.64
     disagre
    1.59
     affor
    1.57
     Mémoires
    1.55
     impra
    1.53
     Chapitre
    1.50
     increa
    1.47
     ftu
    1.46
     Præ
    1.46
     Messieurs
    1.46
    Activations Density 0.181%

    No Known Activations