© 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. 1-RES-JB
    11. 16870
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hood
    -0.71
     Pen
    -0.70
     wast
    -0.66
     Issue
    -0.61
     Hang
    -0.60
     nudity
    -0.59
    inged
    -0.59
     blot
    -0.58
     Hamm
    -0.58
     Weight
    -0.57
    POSITIVE LOGITS
    ":"/
    0.78
    respective
    0.73
    asio
    0.72
    wikipedia
    0.70
    akin
    0.69
    iqueness
    0.68
    Í
    0.67
    ãģ®éŃĶ
    0.67
    Rober
    0.67
    resist
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.