© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dustin"

    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
    341
    +0.09
    0.3%
    1335
    +0.09
    0.2%
    1413
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.09
    283
    +0.09
    0.03
    1120
    +0.08
    0.08
    Negative Logits
     nos
    -0.84
     am
    -0.79
     des
    -0.77
    ModelBuilder
    -0.73
     vol
    -0.73
     co
    -0.72
     est
    -0.71
     الوطنيه
    -0.70
     l
    -0.70
     stat
    -0.69
    POSITIVE LOGITS
     encomp
    2.30
     excru
    2.20
     indestru
    2.18
     affor
    2.18
     increa
    2.16
     cushi
    2.15
     indescri
    2.10
     unspeak
    2.10
     shenan
    2.04
     hairc
    2.03
    Activations Density 0.668%

    No Known Activations