© 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. 16810
    Prev
    Next
    INDEX
    Explanations

    words related to speed or urgency

    oai_token-act-pair · gpt-3.5-turbo

    references to urgency or speed

    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
    ighth
    -0.91
    nants
    -0.85
    oil
    -0.82
    rights
    -0.82
    ateral
    -0.80
    uyomi
    -0.78
    ains
    -0.75
    obyl
    -0.75
    odied
    -0.75
    odan
    -0.75
    POSITIVE LOGITS
     hurry
    1.15
     hurried
    0.97
     haste
    0.91
     rush
    0.89
     hur
    0.81
     scram
    0.80
     hast
    0.76
     Dres
    0.75
     impatient
    0.75
     excuse
    0.73
    Activations Density 0.019%

    No Known Activations