© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    information related to knitting techniques and projects, particularly emphasizing the action of knitting

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    172
    +0.11
    0.3%
    703
    +0.10
    0.3%
    920
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.03
    300
    +0.10
    0.02
    204
    +0.10
    0.02
    Negative Logits
    ScopeManager
    -0.64
    مصادر
    -0.61
    weile
    -0.58
    genöss
    -0.57
     سياس
    -0.56
    riwal
    -0.54
    osa
    -0.54
    localctx
    -0.54
    ABASES
    -0.53
    PANY
    -0.53
    POSITIVE LOGITS
     knit
    2.28
     Knit
    2.04
    Knit
    2.02
    knit
    1.88
     knitting
    1.85
     knitted
    1.82
     Knitting
    1.71
    knitted
    1.50
     impra
    1.30
     affor
    1.29
    Activations Density 0.226%

    No Known Activations