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. 6113
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical warnings and side effects of medication

    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
    +0.29
    1.1%
    453
    +0.08
    0.3%
    1343
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.29
    0.01
    117
    +0.08
    0.03
    852
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.18
    جغرافيا
    -0.66
     held
    -0.65
     hold
    -0.65
    public
    -0.65
    力
    -0.65
     put
    -0.64
     Савез
    -0.63
     run
    -0.62
    </tbody>
    -0.61
    POSITIVE LOGITS
     affor
    1.94
     maneu
    1.83
     accla
    1.72
     volunte
    1.71
     increa
    1.70
     Confe
    1.69
     disagre
    1.68
     fortn
    1.68
     stockholm
    1.67
     milf
    1.65
    Activations Density 0.462%

    No Known Activations