© 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. 16852
    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
    ritical
    -0.77
    Hamilton
    -0.74
    bold
    -0.72
    EStreamFrame
    -0.69
    brush
    -0.69
    PsyNetMessage
    -0.67
     Obj
    -0.67
    Thom
    -0.66
    letters
    -0.65
    trop
    -0.65
    POSITIVE LOGITS
    ching
    0.66
    itus
    0.65
     parasite
    0.65
    ished
    0.62
    ches
    0.61
     lizard
    0.60
    ishment
    0.60
     Jenny
    0.59
    inary
    0.59
    ired
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.