Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13407
    Prev
    Next
    INDEX
    Explanations

    information related to wrestling events and personalities

    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
    +0.12
    0.4%
    1042
    +0.10
    0.3%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    915
    +0.12
    0.03
    1038
    +0.10
    0.02
    48
    +0.10
    0.02
    Negative Logits
     effe
    -1.50
     nece
    -1.49
     aen
    -1.47
     ftu
    -1.46
     thut
    -1.44
     fup
    -1.42
     pollut
    -1.41
     fto
    -1.41
     fta
    -1.39
     fep
    -1.36
    POSITIVE LOGITS
     WWE
    0.82
     wrestler
    0.75
     wrestlers
    0.74
     wrestling
    0.74
    WWE
    0.74
     Wrestling
    0.70
    restling
    0.65
     WrestleMania
    0.65
    Wrestling
    0.59
     backstage
    0.57
    Activations Density 0.232%

    No Known Activations