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. 88
    Prev
    Next
    INDEX
    Explanations

    names

    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
    31
    +0.14
    0.6%
    1763
    +0.12
    0.5%
    1994
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.14
    0.11
    2044
    +0.12
    0.08
    1177
    +0.10
    0.02
    Negative Logits
     McInt
    -0.99
     McLaugh
    -0.90
    ⓧ
    -0.81
     Cuth
    -0.73
     Thacker
    -0.73
     McF
    -0.72
    <bos>
    -0.70
    orothy
    -0.69
     McKin
    -0.68
     bacilli
    -0.67
    POSITIVE LOGITS
     kade
    0.95
     panik
    0.93
     Bibl
    0.92
     makro
    0.91
     kram
    0.91
     kase
    0.89
     Lombar
    0.89
     Rektor
    0.88
     Kanada
    0.88
     Doktor
    0.87
    Activations Density 0.298%

    No Known Activations