© 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. 1-RES-JB
    11. 5515
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the intensity of an action

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers related to strong emotions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allas
    -0.79
    ulhu
    -0.76
     Hebdo
    -0.76
    ombie
    -0.75
     Thumbnails
    -0.74
    animate
    -0.72
    quickShipAvailable
    -0.71
    arnaev
    -0.71
    vertis
    -0.69
    oppers
    -0.69
    POSITIVE LOGITS
     vigorously
    1.17
     vehemently
    0.95
     fought
    0.82
     pursued
    0.81
     hotly
    0.78
    itud
    0.77
     challeng
    0.77
    FIELD
    0.76
     denies
    0.75
     stren
    0.75
    Activations Density 0.008%

    No Known Activations