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

    Neuronpedia

    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. 1-RES-JB
    11. 22523
    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
    enture
    -0.78
    eers
    -0.69
    ensical
    -0.67
    reau
    -0.66
    ctic
    -0.66
     reconc
    -0.65
    agonists
    -0.65
    braska
    -0.64
    bable
    -0.63
    nan
    -0.63
    POSITIVE LOGITS
     ç¥ŀ
    0.73
    è¦
    0.73
    ãĢij
    0.73
    åĨ
    0.72
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    ãĥĺãĥ©
    0.70
    ä¸į
    0.67
    GMT
    0.66
    é¾įå¥ij士
    0.66
    ç¥ŀ
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.