© 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. 16313
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical violence or medical emergencies involving the heart

    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
    946
    +0.11
    0.3%
    1343
    +0.10
    0.3%
    468
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.11
    0.05
    972
    +0.10
    0.04
    100
    +0.09
    0.03
    Negative Logits
     solidar
    -0.77
     frambo
    -0.71
     krim
    -0.71
     marte
    -0.71
     ananas
    -0.70
     kaos
    -0.69
     seyn
    -0.69
     tempel
    -0.68
     rente
    -0.67
     banane
    -0.67
    POSITIVE LOGITS
    !
    0.62
    !!
    0.55
    !!!
    0.53
     phénomènes
    0.51
     nephe
    0.51
     EMERG
    0.49
     stop
    0.49
    !,
    0.48
    Scales
    0.47
     please
    0.47
    Activations Density 0.269%

    No Known Activations