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. 1600
    Prev
    Next
    INDEX
    Explanations

    references to emergency situations, police involvement, and distress calls

    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
    1276
    +0.11
    0.3%
    961
    +0.09
    0.3%
    1053
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.11
    0.04
    1490
    +0.09
    0.04
    961
    +0.09
    0.03
    Negative Logits
     febr
    -0.60
    ♀
    -0.50
     majest
    -0.46
    limsy
    -0.46
    brahim
    -0.45
     Niveau
    -0.45
    ntesis
    -0.44
     cerve
    -0.44
     maig
    -0.44
     pels
    -0.43
    POSITIVE LOGITS
     swarovski
    0.97
     call
    0.94
     hairc
    0.94
     calling
    0.92
     hentai
    0.90
     callers
    0.89
     unspeak
    0.89
     Calling
    0.85
     McInt
    0.84
    calling
    0.83
    Activations Density 0.099%

    No Known Activations