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. 551
    Prev
    Next
    INDEX
    Explanations

    titles of theater productions

    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
    0.6%
    1842
    +0.11
    0.4%
    468
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1297
    +0.18
    0.05
    138
    +0.11
    0.06
    2047
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.27
     initComponents
    -0.96
    SequentialGroup
    -0.92
    <!--[
    -0.92
    GroupLayout
    -0.90
    GIVEREF
    -0.90
    {{--
    -0.88
     jsPsych
    -0.84
    estacks
    -0.80
    GIH
    -0.79
    POSITIVE LOGITS
     maneu
    2.77
     increa
    2.76
     affor
    2.68
     impra
    2.58
     strick
    2.54
     scrat
    2.48
     reluct
    2.45
     emphat
    2.45
     perfet
    2.43
     fuf
    2.41
    Activations Density 0.576%

    No Known Activations