© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 292
    Prev
    Next
    INDEX
    Explanations

    keynote speaker information from event summaries

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1708
    +0.10
    0.3%
    605
    +0.08
    0.2%
    1262
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.04
    690
    +0.08
    0.05
    783
    +0.07
    0.04
    Negative Logits
    Enum
    -0.57
    Ty
    -0.56
    numel
    -0.55
    ima
    -0.54
     Ty
    -0.54
     Lock
    -0.53
    obj
    -0.53
     O
    -0.53
     obj
    -0.50
    Loja
    -0.50
    POSITIVE LOGITS
     keynote
    1.29
     Keynote
    1.22
     beverly
    1.20
     veneta
    1.18
     fte
    1.18
     jaya
    1.17
     toscana
    1.17
     signora
    1.14
     😭😭
    1.13
     dises
    1.11
    Activations Density 0.322%

    No Known Activations