© 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. 22767
    Prev
    Next
    INDEX
    Explanations

    words related to ink, especially in the context of printers and tattoos

    oai_token-act-pair · gpt-3.5-turbo

    references to ink or writing materials

    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
     Sym
    -0.69
     exceptional
    -0.68
     hunting
    -0.66
     tr
    -0.66
     total
    -0.66
     guaranteed
    -0.64
     num
    -0.64
     repeated
    -0.63
     tract
    -0.63
     condemned
    -0.62
    POSITIVE LOGITS
    inks
    4.84
    ink
    2.47
    INK
    2.22
    inking
    2.20
    inker
    1.77
    inky
    1.65
    ooks
    1.29
    insky
    1.25
    inski
    1.19
    itters
    1.18
    Activations Density 0.006%

    No Known Activations