© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    descriptions of geographical locations and construction projects

    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
    674
    +0.12
    0.3%
    964
    +0.08
    0.2%
    1241
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1477
    +0.12
    0.07
    1114
    +0.08
    0.04
    705
    +0.07
    0.03
    Negative Logits
     increa
    -1.63
     maneu
    -1.50
     fuf
    -1.49
     impra
    -1.49
     wherea
    -1.48
     affor
    -1.48
     thut
    -1.47
     guarante
    -1.47
     reluct
    -1.47
     inev
    -1.47
    POSITIVE LOGITS
     equally
    0.73
     deeper
    0.67
    nanoTime
    0.61
     تعدى
    0.61
     overlooked
    0.60
    另一
    0.60
     também
    0.59
     quieter
    0.58
     actually
    0.58
     closer
    0.58
    Activations Density 1.077%

    No Known Activations