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. 1747
    Prev
    Next
    INDEX
    Explanations

    instances of phrases reflecting stories, real-life experiences, and societal observations

    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
    1385
    +0.14
    0.4%
    1317
    +0.13
    0.4%
    1870
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.14
    0.07
    498
    +0.13
    0.03
    1116
    +0.13
    0.04
    Negative Logits
    Xar
    -0.53
    část
    -0.46
    Viited
    -0.46
     himself
    -0.45
     myself
    -0.44
    Begriffsklä
    -0.43
    Sklici
    -0.43
     spécialistes
    -0.42
    Izvori
    -0.42
    Παραπομπές
    -0.41
    POSITIVE LOGITS
     monaster
    0.82
     balon
    0.73
     beren
    0.72
     fono
    0.72
     cristian
    0.72
     ortop
    0.69
     sement
    0.68
    Their
    0.67
     incess
    0.66
    selves
    0.66
    Activations Density 0.467%

    No Known Activations