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. 10023
    Prev
    Next
    INDEX
    Explanations

    mentions of American football games and political controversies

    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
    184
    +0.31
    1.1%
    674
    +0.25
    0.9%
    764
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.03
    1531
    +0.25
    0.03
    1519
    +0.20
    0.03
    Negative Logits
     jacobs
    -0.59
     vincent
    -0.57
     zc
    -0.57
     alexander
    -0.56
     impra
    -0.55
     Expt
    -0.55
     Addr
    -0.55
    filelist
    -0.55
     stefan
    -0.54
     uninten
    -0.54
    POSITIVE LOGITS
     CiNii
    0.68
     >=",
    0.61
     divertente
    0.58
    rrggbb
    0.57
     frasi
    0.56
     poveznice
    0.56
    ⓧ
    0.55
    −/−
    0.54
     disegni
    0.54
     onStop
    0.53
    Activations Density 0.244%

    No Known Activations