© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3466
    Prev
    Next
    INDEX
    Explanations

    terms related to immediate actions or responses

    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
    50
    +0.23
    1.6%
    678
    +0.09
    0.6%
    1385
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.23
    0.11
    1575
    +0.09
    0.11
    678
    +0.08
    0.12
    Negative Logits
    <bos>
    -3.95
     put
    -0.77
    .
    -0.76
     come
    -0.75
     do
    -0.75
    
    -0.74
    /***
    -0.73
    else
    -0.73
     also
    -0.73
    <?
    -0.73
    POSITIVE LOGITS
     napoli
    2.01
     milano
    1.91
     santiago
    1.91
     frankfurt
    1.88
     bandung
    1.87
     stockholm
    1.87
     ricardo
    1.85
     Juf
    1.84
     wien
    1.84
     maroc
    1.82
    Activations Density 1.308%

    No Known Activations