© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3706
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up for events or newsletters

    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
    +0.12
    0.4%
    1757
    +0.12
    0.4%
    82
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    712
    +0.12
    0.02
    82
    +0.12
    0.02
    1757
    +0.10
    0.02
    Negative Logits
     minimalis
    -0.82
     alkoh
    -0.81
     Strukt
    -0.78
     konserv
    -0.75
     solidar
    -0.75
     praktik
    -0.73
     monaster
    -0.73
     keten
    -0.71
     €)
    -0.71
     romero
    -0.70
    POSITIVE LOGITS
     signup
    0.89
     Ename
    0.74
     cushi
    0.73
     Uptake
    0.72
     disreg
    0.71
    signup
    0.71
     McLaugh
    0.68
     reluct
    0.67
     unspeak
    0.67
     plenti
    0.67
    Activations Density 0.056%

    No Known Activations