© 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. 10-RES-JB
    11. 11067
    Prev
    Next
    INDEX
    Explanations

    excitement or anticipation related expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.75
    putable
    -0.71
    iciency
    -0.68
     flaw
    -0.60
    avis
    -0.58
     Dalai
    -0.57
     discredited
    -0.56
    å¦
    -0.56
     restraining
    -0.55
     Settlement
    -0.54
    POSITIVE LOGITS
     about
    0.97
    ly
    0.93
     anticipation
    0.85
    About
    0.81
    lead
    0.76
     bout
    0.73
    LY
    0.72
     excited
    0.71
     About
    0.71
    beat
    0.70
    Activations Density 0.064%

    No Known Activations