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. 13576
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports plays or events

    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
    906
    +0.15
    0.4%
    736
    +0.13
    0.4%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.05
    1689
    +0.13
    0.04
    392
    +0.10
    0.03
    Negative Logits
     wien
    -1.17
     effe
    -1.10
     „,
    -1.09
     resear
    -1.07
     gmbh
    -1.04
     socie
    -1.04
     milano
    -1.03
     ?...
    -1.03
     increa
    -1.03
     meis
    -1.03
    POSITIVE LOGITS
    <bos>
    0.75
    Referencoj
    0.71
    Externé
    0.68
    Atsauces
    0.67
    Prí
    0.64
    Kanpo
    0.64
    Referencies
    0.60
    Și
    0.60
    Čo
    0.59
    GraphicsUnit
    0.58
    Activations Density 0.154%

    No Known Activations