© 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. 10-RES-JB
    11. 5221
    Prev
    Next
    INDEX
    Explanations

    references to technology components and specifications

    oai_token-act-pair · gpt-3.5-turbo

    specific brands or models of technology and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leaks
    -0.55
    urden
    -0.51
    imilation
    -0.51
    fw
    -0.51
    Report
    -0.50
    Giving
    -0.49
    _.
    -0.48
    utra
    -0.48
    âĶĢ
    -0.48
    examination
    -0.48
    POSITIVE LOGITS
     other
    0.79
     others
    0.79
     assorted
    0.76
     Other
    0.69
     Others
    0.68
     hybrids
    0.66
     Miscellaneous
    0.65
     OTHER
    0.62
    other
    0.61
     newer
    0.59
    Activations Density 0.726%

    No Known Activations