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. 496
    Prev
    Next
    INDEX
    Explanations

    surprising or startling events or behavior

    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
    +0.10
    0.3%
    1392
    +0.09
    0.2%
    1643
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.10
    0.05
    652
    +0.09
    0.05
    838
    +0.07
    0.04
    Negative Logits
     GoogleFonts
    -0.58
     justement
    -0.54
     tami
    -0.54
     LIRE
    -0.50
     cier
    -0.50
     Áng
    -0.49
     migli
    -0.48
    elow
    -0.47
     favorece
    -0.47
     soffer
    -0.47
    POSITIVE LOGITS
    shocked
    0.83
     shocked
    0.82
     shock
    0.80
     astonished
    0.76
     surprised
    0.72
     amazed
    0.71
     astonishment
    0.70
     stunned
    0.70
    shock
    0.68
     SHOCK
    0.67
    Activations Density 0.267%

    No Known Activations