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. 14876
    Prev
    Next
    INDEX
    Explanations

    names of comic book characters, especially Wolverine and X-Men characters

    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
    1262
    +0.16
    0.9%
    1506
    +0.16
    0.8%
    120
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.16
    0.00
    1984
    +0.16
    0.06
    227
    +0.15
    0.06
    Negative Logits
    <bos>
    -0.90
    ViewFeatures
    -0.72
    ||}
    -0.60
    zhu
    -0.60
    off
    -0.58
    contentLoaded
    -0.57
    Zhu
    -0.57
    новниш
    -0.57
    fillType
    -0.56
     <>",
    -0.56
    POSITIVE LOGITS
     leonardo
    1.10
     wolverine
    0.94
     philanth
    0.93
     Cæsar
    0.92
     volunte
    0.91
     pamph
    0.89
     Whence
    0.88
     riviera
    0.87
     logan
    0.86
     beaute
    0.85
    Activations Density 0.653%

    No Known Activations