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. 1372
    Prev
    Next
    INDEX
    Explanations

    word sequences related to bed bugs infestations, including terms like "infestation," "insects," "bite," "itch," and methods for treating and getting rid of bed bugs

    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
    946
    +0.10
    0.3%
    198
    +0.09
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1220
    +0.10
    0.03
    944
    +0.09
    0.02
    394
    +0.09
    0.03
    Negative Logits
    RTDA
    -0.77
     partecipa
    -0.73
    dicionado
    -0.69
     Rektor
    -0.68
    DoubleQuotes
    -0.68
     оригіналу
    -0.67
     كومونز
    -0.67
    RectangleBorder
    -0.66
     geograf
    -0.66
     وتسجيلات
    -0.66
    POSITIVE LOGITS
     withal
    1.18
     disagre
    1.09
     apprehen
    1.03
     gaily
    1.03
     tolerably
    1.03
     unspeak
    1.03
     impelled
    1.00
     shewn
    1.00
     pymysql
    0.99
     vainly
    0.95
    Activations Density 0.293%

    No Known Activations