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

    Neuronpedia

    APICircuit 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. 5493
    Prev
    Next
    INDEX
    Explanations

    quotes or statements containing words related to potential threats or dangers

    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
    +0.18
    0.9%
    871
    +0.12
    0.6%
    341
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.18
    0.03
    869
    +0.12
    0.03
    630
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.31
    append
    -0.72
     respond
    -0.70
    console
    -0.70
    struct
    -0.68
     put
    -0.68
     accept
    -0.68
    Println
    -0.67
    BUYER
    -0.67
    print
    -0.66
    POSITIVE LOGITS
     affor
    1.96
     casio
    1.92
     milano
    1.89
     bordeaux
    1.89
     dises
    1.88
     stockholm
    1.88
     riviera
    1.86
     ibiza
    1.86
     napoli
    1.85
     eiffel
    1.84
    Activations Density 0.127%

    No Known Activations