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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7955
    Prev
    Next
    INDEX
    Explanations

    the word "others" or variations such as "Other" and "othering."

    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
    521
    +0.12
    0.4%
    897
    +0.12
    0.4%
    421
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1861
    +0.12
    0.04
    521
    +0.12
    0.03
    1235
    +0.12
    0.03
    Negative Logits
    Mó
    -0.61
    Conheça
    -0.57
    Producción
    -0.54
    Nascimento
    -0.53
    adjacency
    -0.53
    Psico
    -0.53
    Saiba
    -0.52
    Procedimiento
    -0.52
    Fase
    -0.52
    Certific
    -0.51
    POSITIVE LOGITS
     unspeak
    0.84
     tolerably
    0.81
     pamph
    0.79
     liberality
    0.79
     unlaw
    0.78
     milf
    0.78
     gaily
    0.78
     fucker
    0.77
     ardour
    0.77
     nobly
    0.77
    Activations Density 0.063%

    No Known Activations