© 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. 16776
    Prev
    Next
    INDEX
    Explanations

    the word "bored" with different degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of boredom

    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
     annex
    -0.68
     Lomb
    -0.67
     Lucia
    -0.67
     Slovenia
    -0.66
     Kou
    -0.65
     Coch
    -0.61
     Luxembourg
    -0.61
     Flowers
    -0.61
     Ivanka
    -0.60
     Kamp
    -0.60
    POSITIVE LOGITS
    icion
    0.88
    oad
    0.87
    ||||
    0.86
     bored
    0.84
     repetition
    0.76
    icip
    0.75
    hound
    0.74
    dit
    0.71
    bots
    0.71
    jong
    0.71
    Activations Density 0.025%

    No Known Activations