© 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. 4-RES-JB
    11. 4046
    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
    ERY
    -0.75
    jri
    -0.70
     thous
    -0.69
     continuity
    -0.65
    erers
    -0.63
    venture
    -0.63
     Peg
    -0.62
     Cind
    -0.62
    0200
    -0.60
    ãĥ¼ãĥĨãĤ£
    -0.60
    POSITIVE LOGITS
    itational
    0.68
    VERTISEMENT
    0.67
    EngineDebug
    0.66
    \"
    0.65
    \",
    0.64
    ospons
    0.64
    inventoryQuantity
    0.60
     ½
    0.59
     Dism
    0.58
     CLSID
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.