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. 8350
    Prev
    Next
    INDEX
    Explanations

    expressions of support or opposition towards certain entities or causes, including political figures and legislative 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
    573
    +0.12
    0.4%
    347
    +0.11
    0.3%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.12
    0.04
    347
    +0.11
    0.03
    92
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.69
    mybatisplus
    -0.67
    underland
    -0.64
    principalColumn
    -0.62
    ensibility
    -0.59
    calipsis
    -0.59
     mxArray
    -0.59
    énégal
    -0.57
    protoc
    -0.57
    DisplayMetrics
    -0.56
    POSITIVE LOGITS
     depic
    1.57
     shenan
    1.51
     encomp
    1.47
     fortn
    1.37
     increa
    1.37
     strick
    1.36
     unspeak
    1.33
     attemp
    1.33
     intersper
    1.33
     affor
    1.32
    Activations Density 0.191%

    No Known Activations