Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1150
    Prev
    Next
    INDEX
    Explanations

    instances of self-promotion or boasting

    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
    573
    +0.13
    0.4%
    752
    +0.10
    0.3%
    240
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.13
    0.05
    240
    +0.10
    0.03
    16
    +0.09
    0.04
    Negative Logits
    Hozzáférés
    -0.46
    AMILTON
    -0.46
    écial
    -0.44
     schuldig
    -0.43
    unschweig
    -0.43
    .'-
    -0.43
    ErrorException
    -0.43
     dignité
    -0.42
    OrEmpty
    -0.42
     itinéraires
    -0.42
    POSITIVE LOGITS
     Promoted
    0.71
     Promotes
    0.64
     Promote
    0.62
     Promoting
    0.59
     promote
    0.58
     promoting
    0.55
     promotes
    0.55
     promotion
    0.55
     virtues
    0.53
    Promoting
    0.52
    Activations Density 0.317%

    No Known Activations