© 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. 4-RES-JB
    11. 383
    Prev
    Next
    INDEX
    Explanations

    the word "get" at strong activations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I get" or similar expressions indicating understanding or realization

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

    No Comments

    Negative Logits
     Madness
    -0.62
     depiction
    -0.61
    ridge
    -0.61
    cius
    -0.60
     Palestin
    -0.59
     Archdemon
    -0.59
     enclosure
    -0.58
    iege
    -0.57
    enture
    -0.57
     annex
    -0.57
    POSITIVE LOGITS
     rid
    1.10
    tin
    1.02
    TING
    0.96
    aways
    0.85
     bored
    0.80
     lucky
    0.79
     acquainted
    0.76
    terson
    0.76
    DragonMagazine
    0.75
     tired
    0.73
    Activations Density 0.115%

    No Known Activations