© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10752
    Prev
    Next
    INDEX
    Explanations

    mentions of soccer/sports teams and players

    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
    394
    +0.12
    0.4%
    392
    +0.12
    0.4%
    1445
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.12
    0.05
    736
    +0.12
    0.06
    1230
    +0.11
    0.04
    Negative Logits
    VISIONS
    -0.87
    FORMANCE
    -0.80
    EMPT
    -0.78
    NECTIONS
    -0.76
    CRETE
    -0.76
    PLICATION
    -0.72
    CLUDING
    -0.71
    TRIBUTION
    -0.71
     POLLUTION
    -0.70
    MISSIONS
    -0.70
    POSITIVE LOGITS
     accla
    1.70
     Souha
    1.60
     vagu
    1.57
     suspic
    1.55
     embra
    1.53
     Sén
    1.49
     inconce
    1.47
     endom
    1.44
     Membre
    1.43
     shenan
    1.43
    Activations Density 0.298%

    No Known Activations