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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7295
    Prev
    Next
    INDEX
    Explanations

    information related to a car accident, particularly details about the victims, injuries, and authorities' responses

    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
    906
    +0.13
    0.4%
    166
    +0.11
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.05
    166
    +0.11
    0.04
    1487
    +0.10
    0.04
    Negative Logits
     krab
    -0.70
     pól
    -0.70
     quí
    -0.67
     cabrio
    -0.66
     intrig
    -0.65
     vitamine
    -0.65
     robus
    -0.65
     [''
    -0.64
     mondeo
    -0.64
     stihl
    -0.63
    POSITIVE LOGITS
     colliding
    0.63
     collided
    0.61
     accident
    0.61
     collision
    0.60
     McLaugh
    0.60
     speeding
    0.57
     crash
    0.55
     pamph
    0.53
     parked
    0.53
     crashed
    0.52
    Activations Density 0.205%

    No Known Activations