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. 1493
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and outcomes

    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
    1499
    +0.09
    0.2%
    81
    +0.08
    0.2%
    761
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.09
    0.04
    761
    +0.08
    0.04
    536
    +0.08
    0.03
    Negative Logits
     meis
    -0.71
     lusso
    -0.70
     nui
    -0.68
     megane
    -0.66
     andreas
    -0.65
     NOO
    -0.65
     sved
    -0.65
     insegna
    -0.64
     ohr
    -0.63
     !...
    -0.63
    POSITIVE LOGITS
    Wię
    0.69
    Czym
    0.66
    więcej
    0.58
    Gdzie
    0.58
    Dlaczego
    0.58
    Kiedy
    0.57
    Jakie
    0.57
    Przyp
    0.55
     qualify
    0.54
     qualification
    0.53
    Activations Density 0.245%

    No Known Activations