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. 15907
    Prev
    Next
    INDEX
    Explanations

    mentions of sports events and activities

    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
    964
    +0.24
    0.9%
    856
    +0.20
    0.7%
    50
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.24
    0.02
    764
    +0.20
    0.02
    184
    +0.17
    0.01
    Negative Logits
    <bos>
    -0.69
     cioc
    -0.69
     HttpNotFound
    -0.67
     podjela
    -0.62
     gynhyrchwyd
    -0.62
     diverti
    -0.59
     bicic
    -0.58
     cientí
    -0.55
     merav
    -0.54
     Италијани
    -0.53
    POSITIVE LOGITS
     apprehen
    1.68
     vainly
    1.67
     unspeak
    1.60
     gaily
    1.59
     tolerably
    1.58
     disagre
    1.58
     depic
    1.57
     encomp
    1.56
     reluct
    1.52
     impelled
    1.47
    Activations Density 0.084%

    No Known Activations