© 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. 5095
    Prev
    Next
    INDEX
    Explanations

    descriptions of criminal activities and police operations

    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
    382
    +0.11
    0.3%
    1499
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.11
    0.05
    184
    +0.10
    0.02
    1499
    +0.10
    0.04
    Negative Logits
     drap
    -0.66
     krab
    -0.64
     canne
    -0.64
     broderie
    -0.63
     poupée
    -0.63
     ananas
    -0.60
     princesse
    -0.59
     maît
    -0.59
     musiciens
    -0.59
     fendi
    -0.58
    POSITIVE LOGITS
     others
    1.13
     Others
    1.01
    Others
    1.00
    others
    0.96
     OTHERS
    0.74
     remaining
    0.72
     ones
    0.69
     another
    0.67
     Karang
    0.65
     four
    0.65
    Activations Density 0.359%

    No Known Activations