© 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. 0-RES-JB
    11. 14700
    Prev
    Next
    INDEX
    Explanations

    references to specific items made of material

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of sheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ports
    -0.71
    moderate
    -0.68
     moderators
    -0.65
    vale
    -0.64
    icultural
    -0.64
    Domin
    -0.64
    kies
    -0.63
     Cowboy
    -0.63
    olver
    -0.62
    tarian
    -0.62
    POSITIVE LOGITS
     sheet
    4.08
     sheets
    3.30
    sheet
    3.10
     Sheet
    2.99
    sheets
    2.38
    heet
    2.28
     spreadsheet
    1.30
     SHE
    1.22
     parchment
    1.17
     booklet
    1.10
    Activations Density 0.022%

    No Known Activations