© 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. 7090
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ussia
    -0.79
    MpServer
    -0.67
    raviolet
    -0.66
    sie
    -0.65
     fav
    -0.65
    nit
    -0.65
     Caroline
    -0.64
     Gupta
    -0.63
     Stella
    -0.63
     Alma
    -0.62
    POSITIVE LOGITS
     rog
    0.73
    âĶĢâĶĢâĶĢâĶĢ
    0.72
    flight
    0.71
    Merit
    0.69
     Barkley
    0.65
    ewitness
    0.64
     adequ
    0.64
     escal
    0.64
    #$
    0.62
     bounty
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.