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. 3070
    Prev
    Next
    INDEX
    Explanations

    comments or statements in political contexts, including opinions and reactions from various individuals

    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
    2019
    +0.15
    0.4%
    604
    +0.11
    0.3%
    605
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.15
    0.04
    605
    +0.11
    0.02
    2019
    +0.11
    0.05
    Negative Logits
     impra
    -1.47
     shenan
    -1.46
     reluct
    -1.41
     suscep
    -1.40
     increa
    -1.35
     affor
    -1.33
     intermitt
    -1.32
     stickied
    -1.29
     hentai
    -1.29
     cushi
    -1.26
    POSITIVE LOGITS
    ParallelGroup
    0.65
    If
    0.65
    This
    0.64
    It
    0.63
    TRAILING
    0.63
    Inject
    0.62
    Sprintf
    0.60
    DoubleQuotes
    0.60
    Whether
    0.59
    Datuak
    0.59
    Activations Density 0.188%

    No Known Activations