© 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. 6-RES-JB
    11. 8313
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mitt Romney."

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    492
    +0.18
    1.0%
    663
    +0.17
    0.9%
    1178
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.18
    -0.00
    1097
    +0.17
    0.06
    227
    +0.15
    0.06
    Negative Logits
    <bos>
    -0.72
     Günter
    -0.66
     endeavouring
    -0.65
     ardour
    -0.61
     initComponents
    -0.60
     Günther
    -0.58
     belliger
    -0.57
     idolat
    -0.56
     STANLEY
    -0.56
    Sok
    -0.56
    POSITIVE LOGITS
     accogli
    0.73
     abbra
    0.62
     innamor
    0.62
     Ran
    0.62
     Mitt
    0.62
     trovar
    0.61
     casser
    0.61
     pymysql
    0.60
     soggior
    0.60
     psycopg
    0.60
    Activations Density 0.602%

    No Known Activations