© 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. 16386
    Prev
    Next
    INDEX
    Explanations

    words or phrases symbolized by certain characters or patterns, such as 'âĢ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of repeated characters or symbols, particularly for emphasis

    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
     mathemat
    -0.80
     horizont
    -0.71
    enegger
    -0.68
     seiz
    -0.67
     mixed
    -0.66
     tremend
    -0.65
     mosqu
    -0.65
     incidentally
    -0.64
     photoc
    -0.63
     undermin
    -0.63
    POSITIVE LOGITS
    Ľ
    1.20
    ¡
    1.16
    ĸ
    1.15
    ķ
    1.12
    £
    1.11
    ¤
    1.09
    ľ
    1.08
    ¬
    1.08
    ı
    1.08
    į
    1.07
    Activations Density 0.075%

    No Known Activations