© 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. 6882
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are in a unique formatting or are non-standard

    oai_token-act-pair · gpt-3.5-turbo

    instances of high activity or emphasis in the text

    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
     foc
    -0.83
     brid
    -0.81
     clin
    -0.80
     probing
    -0.78
     phased
    -0.77
     mutually
    -0.76
     wills
    -0.75
     mach
    -0.75
     spear
    -0.74
     hiber
    -0.74
    POSITIVE LOGITS
    Advertisement
    1.45
    Also
    1.41
    2
    1.41
    Comment
    1.38
    Related
    1.37
    4
    1.37
    Bonus
    1.36
    Again
    1.35
    Conclusion
    1.35
    Secondly
    1.35
    Activations Density 0.092%

    No Known Activations