© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 4858
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnar
    -0.87
    »Ĵ
    -0.85
    inav
    -0.82
    kefeller
    -0.79
    ihar
    -0.74
    aptic
    -0.73
    æĪ¦
    -0.71
    cyclopedia
    -0.70
    æ³
    -0.70
    Eva
    -0.69
    POSITIVE LOGITS
     smoker
    0.68
     loader
    0.66
     loophole
    0.66
     illegally
    0.63
     backlog
    0.62
     sufficient
    0.62
     fertile
    0.62
     partly
    0.62
     exclusively
    0.61
     unlawfully
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.