© 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. 4-RES-JB
    11. 22108
    Prev
    Next
    INDEX
    Explanations

    names of companies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of companies or corporations

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

    No Comments

    Negative Logits
    BOOK
    -0.86
    */(
    -0.79
    =\"
    -0.73
    =-=-=-=-=-=-=-=-
    -0.71
    lled
    -0.64
    Ò
    -0.63
    yards
    -0.63
    wic
    -0.63
     Halls
    -0.62
    fulness
    -0.62
    POSITIVE LOGITS
    orporated
    1.71
    arcer
    1.29
    orpor
    1.18
    redibly
    1.15
    identally
    1.10
    enture
    1.06
    orp
    1.06
    ursion
    1.02
    endiary
    1.00
    idents
    0.99
    Activations Density 0.008%

    No Known Activations