© 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. 7815
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    company and brand names

    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
     rul
    -0.63
     notor
    -0.62
     customary
    -0.59
     referen
    -0.57
     theoretically
    -0.56
     annexed
    -0.55
     circumst
    -0.55
     doubtful
    -0.55
     conclud
    -0.55
     bombard
    -0.55
    POSITIVE LOGITS
     Brewing
    0.78
    Soul
    0.75
    Dog
    0.72
    Brew
    0.72
    Rock
    0.71
    Heart
    0.70
    Gaming
    0.70
    Sports
    0.70
    Kid
    0.70
    Works
    0.70
    Activations Density 0.642%

    No Known Activations