© 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. 15216
    Prev
    Next
    INDEX
    Explanations

    specific data structure and coding elements

    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
    468
    +0.16
    0.5%
    1510
    +0.13
    0.4%
    1699
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.16
    0.04
    1510
    +0.13
    0.03
    1317
    +0.12
    0.04
    Negative Logits
    Hvor
    -0.80
    Hvem
    -0.78
    Jornal
    -0.78
    Sitio
    -0.77
    Ekster
    -0.75
    Flere
    -0.75
    Specifik
    -0.75
    Več
    -0.73
    Podob
    -0.73
    Hvad
    -0.73
    POSITIVE LOGITS
     fto
    1.70
     !...
    1.65
     effe
    1.62
     „,
    1.57
     blos
    1.53
     squa
    1.52
     sii
    1.52
     fte
    1.52
     fta
    1.51
     ?...
    1.50
    Activations Density 0.234%

    No Known Activations