Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13076
    Prev
    Next
    INDEX
    Explanations

    Daryl Hall's name in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the text delimiter, indicating the separation of entries or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bulg
    -0.76
     Pry
    -0.68
     slurs
    -0.65
     Crusade
    -0.64
     Hera
    -0.63
    terday
    -0.61
     Nun
    -0.61
     Beau
    -0.59
     Verge
    -0.58
     Io
    -0.58
    POSITIVE LOGITS
    iscovery
    1.33
    etermin
    1.30
    etermination
    1.28
    ynam
    1.26
    owntown
    1.26
    ownt
    1.23
    irection
    1.21
    rones
    1.19
    ynasty
    1.18
    imensional
    1.17
    Activations Density 0.055%

    No Known Activations