© 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. 7-RES-JB
    11. 4102
    Prev
    Next
    INDEX
    Explanations

    references to historical events and locations

    oai_token-act-pair · gpt-3.5-turbo

    aspects of movies and television shows related to their narrative or production elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deterrent
    -0.64
    ependent
    -0.62
    missible
    -0.60
     discrim
    -0.60
    PLA
    -0.59
     inhibit
    -0.58
    NRS
    -0.57
     prescribe
    -0.57
     prescribing
    -0.57
    missive
    -0.56
    POSITIVE LOGITS
     hilar
    0.72
    RIP
    0.70
     alas
    0.68
     oddly
    0.66
     Weird
    0.66
     dunno
    0.65
    Yep
    0.65
     admittedly
    0.65
     Conan
    0.65
     curiously
    0.64
    Activations Density 1.139%

    No Known Activations