© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    words related to ink or writing instruments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ink" and related variations

    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
    Community
    -0.76
     Rudolph
    -0.68
    mens
    -0.67
    RC
    -0.65
    Tra
    -0.64
    walking
    -0.62
    Maria
    -0.60
     Community
    -0.60
    Child
    -0.60
    tra
    -0.60
    POSITIVE LOGITS
     ink
    4.12
     Ink
    2.50
     handwriting
    1.44
     pencil
    1.35
     pens
    1.34
     pen
    1.34
     pigment
    1.24
     dye
    1.21
     squid
    1.15
     printer
    1.14
    Activations Density 0.015%

    No Known Activations