Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 24
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to medical terms

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1983
    +0.08
    0.3%
    1735
    +0.08
    0.3%
    50
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.05
    1735
    +0.08
    0.03
    144
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.09
    build
    -0.62
    public
    -0.62
    export
    -0.61
    лык
    -0.60
     moved
    -0.59
     buồn
    -0.59
     consider
    -0.58
    ativistic
    -0.58
     build
    -0.58
    POSITIVE LOGITS
     increa
    1.85
     affor
    1.80
     maneu
    1.75
     SOO
    1.60
     accla
    1.59
     volunte
    1.57
     strick
    1.57
     resear
    1.56
     guarante
    1.55
     effe
    1.55
    Activations Density 0.206%

    No Known Activations