© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    words related to excitement, specifically heightened emotions like thrill and exhilaration

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to thrill and excitement

    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
    avis
    -0.76
    yang
    -0.71
    beard
    -0.71
    apple
    -0.71
    gemony
    -0.69
    amn
    -0.69
    esson
    -0.68
    lder
    -0.67
     leveled
    -0.63
    pex
    -0.63
    POSITIVE LOGITS
     thrill
    1.32
     exhilar
    1.05
    ĸļ
    1.01
     adrenaline
    0.97
     pleasure
    0.95
     excitement
    0.90
     thrilling
    0.81
    ride
    0.77
    ographed
    0.76
    OUP
    0.75
    Activations Density 0.015%

    No Known Activations