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. 13597
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and related information

    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
    1136
    +0.08
    0.2%
    227
    +0.08
    0.2%
    792
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.08
    0.06
    1136
    +0.08
    0.05
    1496
    +0.08
    0.04
    Negative Logits
     ftu
    -1.20
     aen
    -1.13
     fup
    -1.12
     mef
    -1.05
     unlaw
    -1.05
     impractica
    -1.04
     fta
    -1.03
     reft
    -1.03
     poff
    -0.99
     effe
    -0.98
    POSITIVE LOGITS
     lifetime
    0.64
    lifetime
    0.54
     accumulated
    0.54
     career
    0.52
     acum
    0.52
     cumulative
    0.48
     longo
    0.47
    Career
    0.47
    career
    0.47
     Lifetime
    0.47
    Activations Density 0.554%

    No Known Activations