© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13700
    Prev
    Next
    INDEX
    Explanations

    patterns related to user interaction with newsletters or subscriptions

    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
    674
    +0.17
    0.5%
    1343
    +0.14
    0.4%
    453
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1702
    +0.17
    0.02
    1237
    +0.14
    0.02
    595
    +0.12
    0.02
    Negative Logits
     getCity
    -0.63
     McLaugh
    -0.62
     barbarous
    -0.56
     userModel
    -0.56
    asmuch
    -0.55
     itemList
    -0.55
     Punj
    -0.54
     unspeak
    -0.54
     liberality
    -0.54
    olsom
    -0.53
    POSITIVE LOGITS
     anse
    0.83
     obb
    0.82
     cyr
    0.78
     scol
    0.78
     rege
    0.75
     obiet
    0.74
     attes
    0.73
     affez
    0.72
     reger
    0.72
     obligator
    0.72
    Activations Density 0.047%

    No Known Activations