© 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. 7147
    Prev
    Next
    INDEX
    Explanations

    sizes and measurements, especially on a microscopic scale

    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
     entitlement
    -0.66
     Ready
    -0.65
     camping
    -0.65
     Saving
    -0.64
     elig
    -0.64
     AFTER
    -0.64
     withholding
    -0.64
     Healer
    -0.63
     benches
    -0.62
     Started
    -0.62
    POSITIVE LOGITS
     wavelength
    1.17
    ograms
    1.08
     nan
    1.07
     atoms
    1.04
     centimeters
    1.02
    ousand
    1.01
     diameter
    1.00
     wavelengths
    1.00
     molecules
    1.00
    imeters
    0.99
    Activations Density 0.138%

    No Known Activations