© 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. 3082
    Prev
    Next
    INDEX
    Explanations

    references to scientific institutes or research centers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include institutional affiliations or research organizations

    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
    soDeliveryDate
    -0.67
     strips
    -0.67
    alan
    -0.65
     toe
    -0.65
    uckles
    -0.65
     siph
    -0.64
    fleet
    -0.64
     certs
    -0.63
    gallery
    -0.63
     tack
    -0.63
    POSITIVE LOGITS
     Experimental
    0.97
     Excellence
    0.95
     Evaluation
    0.93
     Responsibility
    0.93
     Respons
    0.93
     Investigative
    0.92
     Policy
    0.91
     Enhancement
    0.90
     Standards
    0.90
     Promotion
    0.90
    Activations Density 0.078%

    No Known Activations