© 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. 10798
    Prev
    Next
    INDEX
    Explanations

    statements related to sports drafts and player selections

    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
    401
    +0.09
    0.3%
    1042
    +0.09
    0.3%
    108
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.09
    0.03
    1043
    +0.09
    0.03
    177
    +0.07
    0.02
    Negative Logits
     diamant
    -0.67
     vernis
    -0.64
     „,
    -0.63
     Græ
    -0.63
     meis
    -0.63
     polig
    -0.63
     liev
    -0.63
     artig
    -0.61
     cyr
    -0.60
     tuta
    -0.60
    POSITIVE LOGITS
     motherfucker
    0.59
     naquele
    0.58
     frivol
    0.56
    cdon
    0.56
     tryna
    0.54
     mediocrity
    0.53
    <bos>
    0.51
     allocation
    0.50
     picks
    0.50
     pick
    0.49
    Activations Density 0.112%

    No Known Activations