© 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. 2728
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly "Times Square," and mentions of events or activities associated with those locations

    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
    1323
    +0.08
    0.2%
    168
    +0.08
    0.2%
    1938
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    1343
    +0.08
    0.06
    1927
    +0.07
    0.05
    Negative Logits
     مؤرشف
    -0.75
    postmedia
    -0.72
    LayoutPanel
    -0.71
    setAccessible
    -0.70
    InvalidProtocol
    -0.69
    NonNull
    -0.69
     وقت
    -0.68
    Javadoc
    -0.68
    <eos>
    -0.68
     rather
    -0.67
    POSITIVE LOGITS
     depic
    2.28
     maneu
    2.25
     increa
    2.24
     excru
    2.23
     impra
    2.13
     disagre
    2.13
     scrat
    2.12
     accla
    2.11
     unden
    2.11
     philanth
    2.10
    Activations Density 0.403%

    No Known Activations