© 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. 8-RES-JB
    11. 7759
    Prev
    Next
    INDEX
    Explanations

    words related to exclamations or expressions of surprise or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    names or references to characters, possibly in a narrative or dialogue context

    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
    senal
    -0.76
     BMC
    -0.75
     Presence
    -0.70
     Proceedings
    -0.64
     Kinder
    -0.64
     NCT
    -0.62
     Polk
    -0.61
     Scholar
    -0.60
    ¿½
    -0.60
     Median
    -0.59
    POSITIVE LOGITS
    oooo
    1.45
    mmmm
    1.40
    OOOO
    1.33
    aaaa
    1.32
    OOOOOOOO
    1.28
    mmm
    1.24
    ooo
    1.22
    AAAAAAAA
    1.22
    eeee
    1.21
    oooooooo
    1.21
    Activations Density 0.220%

    No Known Activations