© 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 EvalsExportsAPI 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. 11483
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or steps in a sequence

    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
    1978
    +0.28
    1.0%
    382
    +0.16
    0.5%
    381
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.28
    0.10
    382
    +0.16
    0.09
    1978
    +0.15
    0.09
    Negative Logits
    ביוגרפיה
    -0.68
    født
    -0.61
    astéro
    -0.61
     decembrie
    -0.61
     septembrie
    -0.60
     februarie
    -0.60
     noiembrie
    -0.60
    ectoria
    -0.60
     ianuarie
    -0.59
     aprilie
    -0.57
    POSITIVE LOGITS
    Rgds
    0.96
    Ehh
    0.86
     Plusieurs
    0.85
     unlaw
    0.84
    Noice
    0.78
     Leurs
    0.77
     disreg
    0.77
    Yess
    0.76
    YMMV
    0.76
    Tbh
    0.76
    Activations Density 0.449%

    No Known Activations