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. 2296
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hat"

    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
    555
    +0.18
    0.7%
    662
    +0.14
    0.5%
    874
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.18
    0.02
    662
    +0.14
    0.03
    874
    +0.14
    0.02
    Negative Logits
     Bár
    -0.65
     ecru
    -0.63
     كومونز
    -0.61
     bandeau
    -0.59
     backless
    -0.57
    paddingVertical
    -0.57
     inconce
    -0.57
    marginHorizontal
    -0.56
    celona
    -0.54
     hairc
    -0.54
    POSITIVE LOGITS
     hat
    1.42
     Hat
    1.33
     hats
    1.31
    Hat
    1.28
     HAT
    1.17
    hat
    1.15
    HAT
    1.10
     Hats
    1.09
    hats
    1.04
    Hats
    1.03
    Activations Density 0.088%

    No Known Activations