© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17863
    Prev
    Next
    INDEX
    Explanations

    clothing items related to the neck, such as ties, shirts, collars, and necklines

    oai_token-act-pair · gpt-3.5-turbo

    references to neck-related items and injuries

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ========
    -0.68
     Lak
    -0.65
    urity
    -0.65
     Sigma
    -0.64
     Mile
    -0.62
    âĦ¢:
    -0.62
     Outbreak
    -0.62
    ordinary
    -0.62
     Suc
    -0.61
    Hom
    -0.61
    POSITIVE LOGITS
    lace
    1.48
    tie
    1.41
    beard
    1.32
    bones
    1.20
    lines
    1.16
    bone
    1.13
    line
    1.12
    breaker
    0.90
    yard
    0.87
    breakers
    0.87
    Activations Density 0.025%

    No Known Activations