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. 5663
    Prev
    Next
    INDEX
    Explanations

    instances of events or situations occuring

    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
    +0.17
    1.0%
    1671
    +0.14
    0.8%
    1392
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.17
    0.04
    1392
    +0.14
    0.04
    468
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.29
    public
    -0.88
    const
    -0.80
    /**
    
    -0.74
     const
    -0.71
    ///
    -0.71
    alpha
    -0.70
    for
    -0.70
    ve
    -0.69
     promote
    -0.69
    POSITIVE LOGITS
     maneu
    2.29
     wien
    2.20
     affor
    2.20
     volunte
    2.15
     reluct
    2.13
     fta
    2.13
     unden
    2.12
     stockholm
    2.11
     squa
    2.09
     disagre
    2.09
    Activations Density 0.111%

    No Known Activations