© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20179
    Prev
    Next
    INDEX
    Explanations

    phrases related to various professional and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with economic and social services

    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
    enegger
    -0.76
     Oval
    -0.70
     Niet
    -0.68
     Vaugh
    -0.67
     Seym
    -0.67
     Leban
    -0.65
    âĸ¬
    -0.64
     Prix
    -0.62
     Godd
    -0.61
     Berm
    -0.60
    POSITIVE LOGITS
    bots
    0.62
     scams
    0.62
    ocaust
    0.60
     avoidance
    0.57
     fees
    0.57
     fraud
    0.57
     transfers
    0.56
     adjustment
    0.56
    discrimination
    0.55
     counseling
    0.55
    Activations Density 0.561%

    No Known Activations