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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1
    Prev
    Next
    INDEX
    Explanations

    references to academic societies

    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
    50
    +0.09
    0.4%
    893
    +0.07
    0.3%
    1565
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1456
    +0.09
    0.04
    1574
    +0.07
    0.04
    1738
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.71
    var
    -0.76
    hline
    -0.76
     continue
    -0.76
     colspan
    -0.74
    .
    -0.73
    export
    -0.73
     also
    -0.73
     remain
    -0.72
                
    -0.72
    POSITIVE LOGITS
     socie
    2.49
     increa
    2.19
     maneu
    2.16
     affor
    2.15
     stockholm
    2.08
     impra
    2.06
     strick
    2.05
     aen
    2.04
     wien
    2.02
     embodi
    2.00
    Activations Density 0.111%

    No Known Activations