© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12910
    Prev
    Next
    INDEX
    Explanations

    text related to printed messages or slogans on items

    oai_token-act-pair · gpt-3.5-turbo

    references to specific types of clothing, particularly T-shirts with printed messages or images

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    esters
    -0.86
    anship
    -0.86
    imester
    -0.81
    enne
    -0.78
    abase
    -0.78
    Depth
    -0.76
    mediate
    -0.76
    olia
    -0.74
    iltration
    -0.74
    Reviewer
    -0.72
    POSITIVE LOGITS
     swast
    1.19
     logo
    1.12
     logos
    1.11
     initials
    1.08
     likeness
    1.07
     inscribed
    1.01
     inscription
    0.99
     emblem
    0.96
     slogans
    0.92
     slogan
    0.89
    Activations Density 0.515%

    No Known Activations