© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7092
    Prev
    Next
    INDEX
    Explanations

    references to population statistics and growth

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.79
     spar
    -0.74
    PAC
    -0.74
     backstage
    -0.73
    laim
    -0.72
     VIDEOS
    -0.71
    azor
    -0.68
     Tinker
    -0.68
    hack
    -0.68
    reviewed
    -0.67
    POSITIVE LOGITS
     Population
    1.89
    population
    1.85
    Population
    1.83
     population
    1.76
     births
    1.60
     fertility
    1.56
     census
    1.54
     demographic
    1.43
     populations
    1.41
     Census
    1.37
    Activations Density 0.351%

    No Known Activations