© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearance and sensations

    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
    1413
    +0.10
    0.3%
    1013
    +0.10
    0.3%
    1861
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1997
    +0.10
    0.03
    605
    +0.10
    0.01
    1307
    +0.09
    0.03
    Negative Logits
     ?...
    -0.77
     aen
    -0.77
     emphat
    -0.74
     mme
    -0.73
     „,
    -0.72
     proprement
    -0.71
     Vn
    -0.70
     !...
    -0.70
     aben
    -0.69
     fign
    -0.69
    POSITIVE LOGITS
     createContext
    0.56
    <bos>
    0.56
    odziel
    0.54
     looked
    0.50
    žité
    0.50
    küche
    0.49
     зді
    0.49
     vescovo
    0.49
    getBounding
    0.49
    Jakie
    0.48
    Activations Density 0.245%

    No Known Activations