© 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. 7289
    Prev
    Next
    INDEX
    Explanations

    mentions of wolves and wolf-related themes

    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
    31
    +0.15
    0.7%
    1376
    +0.15
    0.7%
    489
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.15
    0.03
    31
    +0.15
    0.02
    144
    +0.12
    0.02
    Negative Logits
    RectangleBorder
    -0.69
    quelize
    -0.62
    RTEE
    -0.61
    withIdentifier
    -0.57
    AttributeSet
    -0.55
    醐
    -0.55
     noten
    -0.54
    RenderAtEndOf
    -0.54
    GTCX
    -0.53
    jsxFileName
    -0.53
    POSITIVE LOGITS
     Wolf
    1.45
     wolf
    1.38
    Wolf
    1.37
     WOLF
    1.29
     Wolves
    1.25
     wolves
    1.25
    wolf
    1.20
    Wolves
    1.19
     Wolfs
    1.12
     WOL
    1.02
    Activations Density 0.145%

    No Known Activations