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. 5594
    Prev
    Next
    INDEX
    Explanations

    sports competition results

    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%
    1499
    +0.09
    0.3%
    453
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.23
    0.08
    1905
    +0.09
    0.08
    736
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.00
     protoimpl
    -0.75
    public
    -0.71
    mergeFrom
    -0.66
    //
    -0.66
    {
    -0.65
    /**
    -0.64
    const
    -0.63
    makeText
    -0.63
    ുറ
    -0.63
    POSITIVE LOGITS
     accla
    2.27
     reluct
    2.00
     maneu
    1.99
     shenan
    1.96
     impra
    1.95
     affor
    1.92
     depic
    1.87
     disagre
    1.84
     snoopy
    1.84
     philanth
    1.80
    Activations Density 0.751%

    No Known Activations