© 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. 15033
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent attacks and responsibility claims

    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
    284
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    1784
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.09
    332
    +0.10
    0.05
    247
    +0.08
    0.05
    Negative Logits
     ?...
    -1.83
     emphat
    -1.80
     desir
    -1.79
     !...
    -1.79
     effe
    -1.75
     accla
    -1.72
     increa
    -1.72
     affor
    -1.71
     unden
    -1.70
     suscep
    -1.69
    POSITIVE LOGITS
    .
    0.83
     while
    0.76
     after
    0.75
    ;
    0.74
     but
    0.74
    。
    0.73
     although
    0.73
     when
    0.73
     for
    0.71
     because
    0.68
    Activations Density 0.483%

    No Known Activations