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. 15880
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to hypothetical scenarios and social issues

    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
    889
    +0.12
    0.4%
    812
    +0.09
    0.3%
    321
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    868
    +0.12
    0.02
    228
    +0.09
    0.03
    1473
    +0.09
    0.01
    Negative Logits
     Inhabitants
    -0.94
     scottish
    -0.93
     tolerably
    -0.90
     volunte
    -0.90
     employes
    -0.86
     disagre
    -0.86
     practition
    -0.85
     guarante
    -0.84
     wherea
    -0.84
     affor
    -0.84
    POSITIVE LOGITS
    <bos>
    0.88
    Faça
    0.58
    Поздрав
    0.58
    Consejos
    0.57
    WebElementEntity
    0.57
    Cuáles
    0.56
    Jeden
    0.56
    Dès
    0.56
    Debido
    0.55
     âme
    0.55
    Activations Density 0.375%

    No Known Activations