© 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. 8-RES-JB
    11. 9065
    Prev
    Next
    INDEX
    Explanations

    strings indicating the end of an article or segment

    oai_token-act-pair · gpt-3.5-turbo

    indicators of additional content or further reading prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.74
     ende
    -0.69
    hement
    -0.67
    ector
    -0.65
     respectively
    -0.64
     hooked
    -0.63
     supervised
    -0.62
    sembly
    -0.61
     intermedi
    -0.61
     whichever
    -0.59
    POSITIVE LOGITS
    âĢ¢
    1.05
    âĻ¦
    0.94
    Comments
    0.91
    âĸº
    0.89
    Tags
    0.86
    Woman
    0.86
    âĹı
    0.82
    Recent
    0.81
    >>>
    0.80
    Report
    0.79
    Activations Density 0.062%

    No Known Activations