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. 474
    Prev
    Next
    INDEX
    Explanations

    mention of specific roles or activities related to a community or organization

    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
    1896
    +0.12
    0.7%
    1363
    +0.12
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.11
    1385
    +0.12
    0.14
    1013
    +0.10
    0.15
    Negative Logits
    <bos>
    -2.34
    char
    -0.96
    pad
    -0.94
    Pad
    -0.93
    Rod
    -0.93
    str
    -0.91
    pop
    -0.91
    trim
    -0.90
    Pa
    -0.89
    string
    -0.88
    POSITIVE LOGITS
     stockholm
    2.54
     eiffel
    2.37
     ecru
    2.35
     madonna
    2.32
     outlander
    2.30
     riviera
    2.29
     venice
    2.26
     milf
    2.26
     jurassic
    2.26
     bordeaux
    2.26
    Activations Density 2.668%

    No Known Activations