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. 1387
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms

    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
    1385
    +0.11
    0.3%
    74
    +0.08
    0.2%
    855
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.11
    0.03
    1948
    +0.08
    0.04
    16
    +0.07
    0.05
    Negative Logits
     impra
    -0.90
     increa
    -0.86
     scrat
    -0.83
     shenan
    -0.82
     reluct
    -0.81
     unden
    -0.80
     encomp
    -0.80
     philanth
    -0.78
     disreg
    -0.77
     downvoted
    -0.77
    POSITIVE LOGITS
    <bos>
    0.64
     maig
    0.60
    glicher
    0.57
    FunctionFlags
    0.56
     ability
    0.55
    Obrigada
    0.55
    Xar
    0.55
    Obrigado
    0.53
    lectual
    0.52
    Autoritní
    0.51
    Activations Density 0.411%

    No Known Activations