© 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. 6-RES-JB
    11. 10766
    Prev
    Next
    INDEX
    Explanations

    ads or commercial content

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grass
    -0.72
     Kut
    -0.68
    itar
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.63
     Roses
    -0.62
     Triangle
    -0.61
    MJ
    -0.61
     Ultr
    -0.60
    ãĥ¯ãĥ³
    -0.60
     Myster
    -0.59
    POSITIVE LOGITS
    Skip
    1.02
    ADVERTISEMENT
    0.96
     Thanks
    0.80
    iciary
    0.79
     Appears
    0.71
    olson
    0.66
     Continued
    0.66
    sylvania
    0.66
    entin
    0.65
    iseum
    0.63
    Activations Density 0.013%

    No Known Activations