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. 1482
    Prev
    Next
    INDEX
    Explanations

    error messages in a specific format

    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
    876
    +0.18
    0.5%
    468
    +0.10
    0.3%
    906
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.18
    -0.00
    1583
    +0.10
    0.02
    1005
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.78
     by
    -0.62
     so
    -0.61
     
    -0.61
    ,
    -0.59
    随着
    -0.56
     and
    -0.56
     via
    -0.56
     победы
    -0.56
     through
    -0.55
    POSITIVE LOGITS
     napoli
    1.74
     milano
    1.72
     nutr
    1.71
     sappi
    1.64
     thermomix
    1.60
     wien
    1.59
     dispen
    1.58
     mef
    1.57
     stockholm
    1.57
     tanga
    1.54
    Activations Density 0.180%

    No Known Activations