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. 727
    Prev
    Next
    INDEX
    Explanations

    groups of people or things that are small in number but significant in the context they are mentioned

    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
    629
    +0.11
    0.3%
    406
    +0.11
    0.3%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.04
    143
    +0.11
    0.04
    629
    +0.09
    0.03
    Negative Logits
     accla
    -0.66
     héro
    -0.62
     étend
    -0.61
     Bk
    -0.59
     Hv
    -0.59
     végétal
    -0.59
     secon
    -0.57
     lts
    -0.57
     Lc
    -0.56
     Ruman
    -0.55
    POSITIVE LOGITS
     handful
    0.92
     few
    0.67
    /**
    0.66
    dozen
    0.60
     select
    0.59
    few
    0.56
     dozen
    0.56
     lucky
    0.56
    Quelques
    0.54
     voulait
    0.54
    Activations Density 0.216%

    No Known Activations