© 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. 4-RES-JB
    11. 10727
    Prev
    Next
    INDEX
    Explanations

    adverbs that emphasize intensity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that express various degrees of intensity or emphasis

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

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.84
    irin
    -0.73
    yond
    -0.72
     Various
    -0.72
    atching
    -0.70
    rying
    -0.70
    wayne
    -0.68
    ESCO
    -0.65
    instance
    -0.64
     Emin
    -0.64
    POSITIVE LOGITS
     owe
    0.95
     forgot
    0.90
     went
    0.88
     knew
    0.86
     owes
    0.85
     tasted
    0.85
     wore
    0.84
     earns
    0.82
     blew
    0.82
     gave
    0.81
    Activations Density 0.297%

    No Known Activations