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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2290
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Charlottesville" along with related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1937
    +0.19
    0.9%
    90
    +0.17
    0.8%
    1520
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.19
    0.03
    1937
    +0.17
    0.03
    1407
    +0.16
    0.02
    Negative Logits
     izvē
    -0.53
    quinha
    -0.53
     ardour
    -0.51
    adona
    -0.50
     Paix
    -0.49
    УДК
    -0.48
    ponge
    -0.47
     Morelos
    -0.46
    ējās
    -0.46
    ristiana
    -0.46
    POSITIVE LOGITS
     Char
    1.42
     char
    1.33
    Char
    1.32
    char
    1.25
     CHAR
    1.23
    CHAR
    1.14
     Charter
    1.04
     Charlie
    1.03
     charter
    1.01
    Charlie
    0.98
    Activations Density 0.077%

    No Known Activations