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. 8327
    Prev
    Next
    INDEX
    Explanations

    actions indicating physical abuse

    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
    1577
    +0.32
    1.2%
    906
    +0.23
    0.9%
    50
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.32
    0.28
    946
    +0.23
    0.18
    906
    +0.18
    -0.04
    Negative Logits
     manuten
    -1.14
     aboli
    -0.99
     susun
    -0.98
     meras
    -0.95
     solidar
    -0.91
     astu
    -0.90
     Autó
    -0.90
     consoli
    -0.89
     CiNii
    -0.89
     hunde
    -0.89
    POSITIVE LOGITS
     tubercle
    0.92
     lamella
    0.92
     friable
    0.89
     sessile
    0.87
     blackish
    0.86
     disreg
    0.85
     whitish
    0.82
     papilla
    0.79
     embodi
    0.78
     ineffec
    0.76
    Activations Density 7.909%

    No Known Activations