© 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. 10-RES-JB
    11. 2658
    Prev
    Next
    INDEX
    Explanations

    bits and pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    references to various physical activities and experiences

    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
    emale
    -0.83
    ĸļ
    -0.79
    definition
    -0.71
    ļéĨĴ
    -0.71
     2025
    -0.69
    heid
    -0.68
    idth
    -0.67
    ounter
    -0.67
    ]=
    -0.66
     2022
    -0.65
    POSITIVE LOGITS
     sprinkled
    1.03
     lately
    0.93
     beforehand
    0.91
     leftover
    0.89
     apiece
    0.86
     ;)
    0.84
     ago
    0.84
     besides
    0.84
     quirks
    0.83
     along
    0.82
    Activations Density 0.366%

    No Known Activations