© 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. 2564
    Prev
    Next
    INDEX
    Explanations

    writers' names and their associated publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of writers and editors in the context of articles or publications

    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
    aceae
    -0.72
    NetMessage
    -0.70
     handshake
    -0.69
    externalActionCode
    -0.69
    iments
    -0.68
     Germans
    -0.65
    catentry
    -0.64
     sequ
    -0.62
     scrim
    -0.61
     ribbon
    -0.61
    POSITIVE LOGITS
     blogs
    0.88
     Journalism
    0.84
     freelance
    0.81
     Featured
    0.79
     blogger
    0.78
     journalism
    0.78
     Editorial
    0.78
     Slate
    0.76
    rint
    0.74
    blogs
    0.73
    Activations Density 0.204%

    No Known Activations