© 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. 0-RES-JB
    11. 22379
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flowers
    -0.72
     Featured
    -0.67
     Daniels
    -0.67
     Comes
    -0.66
    amily
    -0.65
     Sign
    -0.65
     Countdown
    -0.64
     Attributes
    -0.63
    ylum
    -0.63
    abase
    -0.62
    POSITIVE LOGITS
     defe
    0.89
     strugg
    0.87
     newsp
    0.82
     reluct
    0.74
    norm
    0.74
     obser
    0.74
    bent
    0.72
     defic
    0.70
    minist
    0.70
    Gov
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.