© 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. 10-RES-JB
    11. 10669
    Prev
    Next
    INDEX
    Explanations

    phrases related to possessions, transactions, and occupations

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and verbs related to the condition and ownership of items, specifically focusing on used, stolen, and expired items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undrum
    -0.86
    aminer
    -0.84
    committee
    -0.82
    xual
    -0.77
    ittee
    -0.76
    iphany
    -0.73
    robe
    -0.73
    Goal
    -0.73
    ccording
    -0.72
    utra
    -0.71
    POSITIVE LOGITS
     materials
    1.34
     goods
    1.28
     items
    1.25
     material
    1.24
     parts
    1.20
     versions
    1.17
     copies
    1.17
     products
    1.13
     ones
    1.13
     components
    1.11
    Activations Density 0.268%

    No Known Activations