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. 13966
    Prev
    Next
    INDEX
    Explanations

    references to specific times (specific dates, past times), locations, and actions (such as searching and taking actions)

    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
    939
    +0.09
    0.3%
    2019
    +0.09
    0.3%
    856
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.09
    0.06
    1967
    +0.09
    0.04
    1567
    +0.08
    0.03
    Negative Logits
     kado
    -0.71
     kram
    -0.69
     uhr
    -0.67
     palab
    -0.66
     horri
    -0.65
     jaja
    -0.64
     gero
    -0.64
     ingrat
    -0.64
     mercen
    -0.63
     meis
    -0.62
    POSITIVE LOGITS
     amenities
    0.47
    europa
    0.46
     dort
    0.44
    InSection
    0.44
    딪
    0.42
    withIdentifier
    0.42
    そこで
    0.42
    SharedCtor
    0.41
    IntoConstraints
    0.41
     dzies
    0.41
    Activations Density 0.576%

    No Known Activations