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. 8395
    Prev
    Next
    INDEX
    Explanations

    mentions of boxing matches and related details

    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
    304
    +0.10
    0.3%
    1842
    +0.09
    0.3%
    1675
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.10
    0.05
    1675
    +0.09
    0.06
    632
    +0.08
    0.03
    Negative Logits
     pollut
    -0.94
     effe
    -0.90
     vian
    -0.90
     erec
    -0.89
     aen
    -0.87
     dovr
    -0.85
     levis
    -0.83
     mef
    -0.83
     venuto
    -0.82
     guatemala
    -0.81
    POSITIVE LOGITS
     UFC
    0.57
     titles
    0.53
     knockout
    0.53
     undefeated
    0.53
     rematch
    0.52
     brawl
    0.51
     title
    0.51
     trainer
    0.50
     challenger
    0.50
     challeng
    0.50
    Activations Density 0.485%

    No Known Activations