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. 1438
    Prev
    Next
    INDEX
    Explanations

    keywords related to politics, advocacy, and government actions

    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
    394
    +0.17
    0.5%
    50
    +0.14
    0.4%
    783
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.17
    0.07
    1806
    +0.14
    0.07
    783
    +0.12
    0.06
    Negative Logits
     Halen
    -0.76
    <bos>
    -0.76
    Билгалдахарш
    -0.74
     كومونز
    -0.74
     uska
    -0.73
    NOSIS
    -0.72
     ***!
    -0.71
    IDTH
    -0.70
    XMLSchema
    -0.70
    cèse
    -0.70
    POSITIVE LOGITS
     intersper
    2.50
     increa
    2.30
     guarante
    2.22
     impra
    2.17
     inev
    2.17
     encomp
    2.17
     reluct
    2.17
     fta
    2.15
     fuf
    2.14
     purcha
    2.12
    Activations Density 0.445%

    No Known Activations