Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 14513
    Prev
    Next
    INDEX
    Explanations

    call-to-action phrases related to gaining points, earning rewards, and thanking others

    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
    +0.20
    1.2%
    699
    +0.13
    0.7%
    1256
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.20
    0.04
    699
    +0.13
    0.04
    1512
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.16
    public
    -0.78
    const
    -0.74
    //
    -0.72
    HasIndex
    -0.71
    HasAnnotation
    -0.70
    interface
    -0.68
    struct
    -0.67
    ;
    -0.66
    SizeF
    -0.66
    POSITIVE LOGITS
     increa
    1.93
     maneu
    1.92
     stockholm
    1.86
     affor
    1.85
     shenan
    1.74
     impra
    1.73
     wien
    1.69
     unlaw
    1.69
     eiffel
    1.68
     wherea
    1.68
    Activations Density 0.066%

    No Known Activations