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. 16061
    Prev
    Next
    INDEX
    Explanations

    phrases related to crimes or conflict

    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
    1013
    +0.12
    0.3%
    1264
    +0.09
    0.2%
    1876
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1876
    +0.12
    0.05
    1142
    +0.09
    0.05
    284
    +0.08
    0.07
    Negative Logits
     kram
    -1.08
     doman
    -1.02
     ordina
    -1.01
     vernac
    -1.00
     „,
    -1.00
     !...
    -0.98
     glan
    -0.97
     mef
    -0.97
     lele
    -0.95
     Nö
    -0.95
    POSITIVE LOGITS
     by
    0.98
     oleh
    0.68
     przez
    0.66
     bởi
    0.66
    by
    0.62
     توسط
    0.61
     during
    0.59
     ידי
    0.59
     twice
    0.56
     durch
    0.56
    Activations Density 0.346%

    No Known Activations