© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 571
    Prev
    Next
    INDEX
    Explanations

    words related to judgment, evaluation, or criticism

    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
    50
    +0.09
    0.3%
    1909
    +0.08
    0.3%
    82
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1354
    +0.09
    0.04
    1256
    +0.08
    0.03
    935
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.84
    displayquote
    -0.79
    public
    -0.76
    const
    -0.76
    import
    -0.75
    ,
    -0.75
    .
    -0.74
    <tfoot>
    -0.74
    <tbody>
    -0.74
    void
    -0.74
    POSITIVE LOGITS
     maneu
    2.54
     increa
    2.36
     stockholm
    2.30
     affor
    2.28
     impra
    2.24
     Juf
    2.19
     accla
    2.19
     inev
    2.17
     reluct
    2.16
     emphat
    2.16
    Activations Density 0.110%

    No Known Activations