Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1413
    Prev
    Next
    INDEX
    Explanations

    mentions of hair-related terms like "hair salon," "salon," and descriptions of hair

    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
    204
    +0.13
    0.5%
    896
    +0.12
    0.4%
    1026
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.13
    0.02
    896
    +0.12
    0.02
    1026
    +0.11
    0.02
    Negative Logits
     bascul
    -0.51
     ché
    -0.51
    Dawg
    -0.51
     Pockets
    -0.50
     cushi
    -0.48
    mnop
    -0.48
     Stretcher
    -0.47
     Assorted
    -0.47
    Ferdin
    -0.47
     Wrench
    -0.46
    POSITIVE LOGITS
     hair
    1.41
    Hair
    1.32
    hair
    1.29
     Hair
    1.29
     HAIR
    1.23
    HAIR
    1.08
     hairs
    1.00
    haired
    0.99
     haired
    0.92
    hairs
    0.87
    Activations Density 0.078%

    No Known Activations