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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13712
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing and appearances

    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
    1385
    +0.17
    0.5%
    1343
    +0.09
    0.3%
    198
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.06
    1188
    +0.09
    0.02
    1821
    +0.08
    0.04
    Negative Logits
     bandeau
    -1.05
     hairc
    -0.93
     ecru
    -0.92
     legging
    -0.78
     hoody
    -0.75
     Cfr
    -0.71
     pettico
    -0.69
     diffusi
    -0.68
     indiri
    -0.66
     swarovski
    -0.66
    POSITIVE LOGITS
     wearing
    0.57
     dress
    0.57
     attire
    0.56
     triomphe
    0.52
     costume
    0.52
     shoes
    0.50
     luigi
    0.50
    zucht
    0.50
     shirt
    0.50
     worn
    0.49
    Activations Density 0.256%

    No Known Activations