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. 10118
    Prev
    Next
    INDEX
    Explanations

    details of a sports event, particularly boxing matches

    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
    736
    +0.13
    0.4%
    906
    +0.12
    0.4%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.06
    392
    +0.12
    0.02
    1201
    +0.09
    0.02
    Negative Logits
     lele
    -0.93
     istan
    -0.92
     vian
    -0.89
     meis
    -0.88
     ecclesias
    -0.87
     obiet
    -0.86
     sena
    -0.86
     lemp
    -0.85
     liev
    -0.84
     veda
    -0.84
    POSITIVE LOGITS
     aggressor
    0.53
    interrup
    0.49
    Ofer
    0.48
    bcryptjs
    0.47
     pymongo
    0.47
    Tél
    0.47
    griffe
    0.46
     attaques
    0.46
     knockout
    0.46
     opponent
    0.45
    Activations Density 0.248%

    No Known Activations