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. 686
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender bias, emotions, and reactions

    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
    964
    +0.08
    0.2%
    437
    +0.07
    0.2%
    198
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.08
    0.04
    640
    +0.07
    0.05
    584
    +0.07
    0.03
    Negative Logits
    ectoria
    -0.49
    :,,
    -0.45
     précédemment
    -0.45
     |]
    -0.44
     Şi
    -0.44
    ceff
    -0.44
     madden
    -0.43
     détermination
    -0.43
     malheureusement
    -0.43
    enddo
    -0.43
    POSITIVE LOGITS
     pimiento
    0.58
     santiago
    0.56
     paloma
    0.56
     slightest
    0.56
     ļ
    0.53
     venezuela
    0.53
     calavera
    0.51
    quences
    0.50
     enää
    0.49
     seeing
    0.49
    Activations Density 0.361%

    No Known Activations