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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10626
    Prev
    Next
    INDEX
    Explanations

    words related to promoting practical strategies aimed at reducing negative consequences in situations involving risky behaviors

    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
    241
    +0.14
    0.6%
    1437
    +0.14
    0.5%
    1425
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.14
    0.04
    1437
    +0.14
    0.04
    1964
    +0.12
    0.04
    Negative Logits
    ingeki
    -0.45
    raja
    -0.45
    bigcap
    -0.45
     conlle
    -0.44
    Preço
    -0.43
    weta
    -0.43
    楽部
    -0.43
    kasa
    -0.43
    gensen
    -0.42
     Raju
    -0.41
    POSITIVE LOGITS
    Sh
    1.19
     Sh
    1.18
     sh
    1.03
    sh
    0.99
     SH
    0.95
    Sher
    0.87
    SH
    0.87
     Shor
    0.85
    Shan
    0.84
     Sher
    0.84
    Activations Density 0.186%

    No Known Activations