© 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. 3116
    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
    atron
    -0.84
    lette
    -0.76
    dt
    -0.71
    factor
    -0.71
    arette
    -0.68
    entity
    -0.67
     Lone
    -0.67
    horse
    -0.65
    Walker
    -0.65
    roth
    -0.64
    POSITIVE LOGITS
    etheless
    0.74
    ĺħ
    0.68
     foregoing
    0.67
     peacefully
    0.67
     satisf
    0.64
     pressing
    0.64
    alty
    0.63
     earnest
    0.62
     peaceful
    0.61
     mutually
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.