© 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. 14946
    Prev
    Next
    INDEX
    Explanations

    descriptions related to injuries and bleeding

    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
    122
    +0.14
    0.4%
    468
    +0.12
    0.4%
    405
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.14
    0.03
    122
    +0.12
    0.02
    976
    +0.11
    0.02
    Negative Logits
     meras
    -0.57
    fontStyle
    -0.56
     Zweifel
    -0.53
     bú
    -0.51
     Sucher
    -0.51
     Köl
    -0.49
     krem
    -0.49
     asma
    -0.48
    OGND
    -0.48
     tuya
    -0.47
    POSITIVE LOGITS
     bleeding
    1.14
     bleed
    1.09
     Bleeding
    1.06
     bleeds
    1.05
     bled
    0.98
    Bleeding
    0.96
     blood
    0.90
    bleed
    0.85
    blood
    0.83
     împre
    0.80
    Activations Density 0.087%

    No Known Activations