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. 1520
    Prev
    Next
    INDEX
    Explanations

    actions related to collecting items or data

    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
    1166
    +0.09
    0.3%
    1379
    +0.09
    0.3%
    1482
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.09
    0.03
    667
    +0.09
    0.03
    849
    +0.09
    0.03
    Negative Logits
     défend
    -0.73
     reconnaît
    -0.63
     Viene
    -0.62
    cassert
    -0.59
     renfer
    -0.58
     soutient
    -0.57
     résulte
    -0.55
     prévoit
    -0.55
     nomme
    -0.54
     révèle
    -0.53
    POSITIVE LOGITS
     collect
    1.03
    collect
    0.86
     Collect
    0.86
     collects
    0.86
     collected
    0.85
     collecting
    0.83
     COLLECT
    0.82
    collected
    0.82
     gather
    0.79
    collecting
    0.76
    Activations Density 0.229%

    No Known Activations