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. 15227
    Prev
    Next
    INDEX
    Explanations

    references to tribes or tribal communities

    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
    1961
    +0.20
    1.0%
    1892
    +0.12
    0.6%
    555
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1961
    +0.20
    0.02
    227
    +0.12
    0.03
    1026
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.47
     remplace
    -0.57
     de
    -0.51
     rec
    -0.48
    HasAnnotation
    -0.48
    HasColumnType
    -0.47
     harmonize
    -0.47
    ag
    -0.46
     bác
    -0.45
    Externí
    -0.45
    POSITIVE LOGITS
     tribe
    1.34
     Tribe
    1.19
     tribes
    1.14
    Tribe
    1.12
    tribe
    1.09
     chèvre
    1.08
     tribal
    1.07
     napoli
    1.04
     ibiza
    1.03
     Tribes
    1.02
    Activations Density 0.302%

    No Known Activations