© 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. 0-RES-JB
    11. 6883
    Prev
    Next
    INDEX
    Explanations

    ​​​​phrases related to the name "Hum" followed by numbers related to significant figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Hum" related to humor or comedic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KEN
    -0.77
    ocket
    -0.74
    anski
    -0.73
     fisher
    -0.70
    redo
    -0.66
    apolis
    -0.65
    yk
    -0.65
    ãĥİ
    -0.63
    okane
    -0.63
     "$:/
    -0.63
    POSITIVE LOGITS
     Hum
    4.14
    Hum
    2.63
    hum
    2.05
     HUM
    1.75
     hum
    1.61
     Hib
    1.18
     Civ
    1.15
     Chim
    1.11
     Mour
    1.10
     humid
    1.03
    Activations Density 0.018%

    No Known Activations