© 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. 11471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or repetition

    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
    1265
    +0.13
    0.4%
    897
    +0.13
    0.4%
    545
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.13
    0.04
    1194
    +0.13
    0.03
    1265
    +0.12
    0.04
    Negative Logits
     meras
    -0.56
     Spanyol
    -0.52
    -------
    -0.51
     المعيارى
    -0.51
     almas
    -0.49
     gili
    -0.48
    ərbay
    -0.48
     poliuret
    -0.47
    Câ
    -0.47
     alkoh
    -0.47
    POSITIVE LOGITS
     perfon
    0.85
     shewn
    0.85
     feen
    0.80
     gaily
    0.78
     fays
    0.76
     ftu
    0.75
     foon
    0.75
     maneu
    0.74
     guarante
    0.72
     »>
    0.72
    Activations Density 0.106%

    No Known Activations