© 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. 20732
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating emphasis or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    symbols that represent a form of emphasis or exclamation

    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
     cyan
    -0.74
     decomp
    -0.74
     shrouded
    -0.73
     sliding
    -0.69
     collecting
    -0.68
     shroud
    -0.67
     neglig
    -0.67
     scatter
    -0.66
     battered
    -0.66
     shack
    -0.65
    POSITIVE LOGITS
    º
    1.01
    £
    0.95
    ONSORED
    0.92
    ¹
    0.85
    ¦
    0.83
    ¯¯¯¯
    0.82
    ¬
    0.81
    ¯
    0.80
     Ibid
    0.79
    âĢķ
    0.79
    Activations Density 0.124%

    No Known Activations