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. 93
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the consideration of different options or possibilities

    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
    +0.23
    0.8%
    1705
    +0.11
    0.4%
    597
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1831
    +0.23
    0.07
    470
    +0.11
    0.05
    119
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.39
     manage
    -0.69
    所
    -0.63
    render
    -0.61
    document
    -0.61
    console
    -0.61
    emit
    -0.60
    protected
    -0.59
    control
    -0.59
    assert
    -0.59
    POSITIVE LOGITS
     fta
    1.85
     thut
    1.76
     Juf
    1.69
     suspic
    1.69
     fto
    1.68
     ftu
    1.67
     volunte
    1.67
     fte
    1.66
     inev
    1.65
     mef
    1.63
    Activations Density 1.374%

    No Known Activations