© 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. 10-RES-JB
    11. 10751
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical parts and components

    oai_token-act-pair · gpt-3.5-turbo

    references to physical components or parts used in manufacturing and industry

    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
     Patron
    -0.71
     Kard
    -0.69
    culosis
    -0.66
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
    Brave
    -0.65
     Klux
    -0.65
     Skies
    -0.64
     Agenda
    -0.64
     grandparents
    -0.63
    idav
    -0.63
    POSITIVE LOGITS
    meal
    1.04
     thereof
    0.99
    ridges
    0.88
    etting
    0.84
    ridge
    0.78
    isans
    0.77
     kits
    0.77
     kit
    0.76
    ets
    0.73
    ials
    0.73
    Activations Density 0.040%

    No Known Activations