© 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. 18602
    Prev
    Next
    INDEX
    Explanations

    references to the state of Maryland

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Maryland."

    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
     Aires
    -0.80
    =-=-=-=-=-=-=-=-
    -0.79
    yip
    -0.76
    BOOK
    -0.70
    gered
    -0.69
    Brazil
    -0.68
    ample
    -0.65
    module
    -0.65
    ancouver
    -0.64
    herer
    -0.64
    POSITIVE LOGITS
     Orioles
    0.70
     Madness
    0.70
    nuts
    0.70
    itage
    0.67
     Tech
    0.66
     Consolid
    0.64
    arian
    0.64
    ers
    0.63
    esse
    0.63
    edu
    0.62
    Activations Density 0.020%

    No Known Activations