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. 1624
    Prev
    Next
    INDEX
    Explanations

    terms related to military operations or historical events

    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
    +0.27
    1.0%
    137
    +0.14
    0.5%
    1177
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.27
    0.12
    394
    +0.14
    0.08
    1784
    +0.13
    0.09
    Negative Logits
    <bos>
    -0.97
    featureID
    -0.76
    MessageTagHelper
    -0.75
    getWriter
    -0.74
    AndEndTag
    -0.73
    Попис
    -0.73
     Normdatei
    -0.73
    ValueStyle
    -0.72
     Wiktionnaire
    -0.71
    fvar
    -0.68
    POSITIVE LOGITS
     reluct
    2.10
     increa
    2.03
     disagre
    1.95
     shenan
    1.94
     emphat
    1.91
     maneu
    1.90
     inev
    1.89
     encomp
    1.89
     affor
    1.84
     wherea
    1.82
    Activations Density 2.366%

    No Known Activations