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. 294
    Prev
    Next
    INDEX
    Explanations

    instances of the word "played"

    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
    1124
    +0.14
    0.4%
    1778
    +0.13
    0.4%
    421
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1124
    +0.14
    0.06
    1778
    +0.13
    0.05
    1618
    +0.11
    0.04
    Negative Logits
    -------------</
    -0.61
    otes
    -0.52
    XMLSchema
    -0.51
    QName
    -0.51
     Kohlen
    -0.50
    LinkId
    -0.50
    Hauptartikel
    -0.50
    RTSN
    -0.49
    rubin
    -0.48
    блиоте
    -0.48
    POSITIVE LOGITS
     increa
    1.39
     shenan
    1.34
     guarante
    1.29
     fortn
    1.28
     apprehen
    1.27
     hairc
    1.26
     reluct
    1.26
     wherea
    1.25
     snoopy
    1.25
     maneu
    1.25
    Activations Density 0.127%

    No Known Activations