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

    Neuronpedia

    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. 13402
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods or sequenced events related to sports

    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
    674
    +0.10
    0.3%
    1479
    +0.09
    0.2%
    1081
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.10
    0.05
    1225
    +0.09
    0.03
    1479
    +0.09
    0.02
    Negative Logits
     increa
    -1.87
     fuf
    -1.85
     inev
    -1.78
     guarante
    -1.78
     disagre
    -1.77
     wherea
    -1.76
     maneu
    -1.75
     depic
    -1.74
     emphat
    -1.74
     purcha
    -1.72
    POSITIVE LOGITS
     without
    0.78
     knowing
    0.75
    Autoritní
    0.73
    asteroide
    0.73
     with
    0.72
    формление
    0.71
    Με
    0.70
     consultato
    0.68
    without
    0.67
    <bos>
    0.67
    Activations Density 0.266%

    No Known Activations