© 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. 10693
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis, assumptions, and scholarly discourse

    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
    1173
    +0.11
    0.3%
    1265
    +0.11
    0.3%
    1757
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.11
    0.05
    1173
    +0.11
    0.04
    1757
    +0.10
    0.05
    Negative Logits
     mef
    -1.63
     depic
    -1.62
     fte
    -1.62
     aen
    -1.59
     emphat
    -1.59
     effe
    -1.57
     secon
    -1.56
     guarante
    -1.54
     ?...
    -1.53
     fuf
    -1.53
    POSITIVE LOGITS
     albeit
    0.80
     though
    0.76
     however
    0.73
     although
    0.72
    BeginContext
    0.69
    Pues
    0.66
     despite
    0.63
     without
    0.63
    بالإ
    0.62
     perhaps
    0.62
    Activations Density 0.225%

    No Known Activations