© 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. 10-RES-JB
    11. 10031
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes and clothing items

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to body parts or personal possessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.87
    soDeliveryDate
    -0.83
     Recomm
    -0.81
    Quantity
    -0.80
    ablishment
    -0.72
     Administ
    -0.71
     Quantity
    -0.68
    artifacts
    -0.68
    quickShipAvailable
    -0.67
    acebook
    -0.66
    POSITIVE LOGITS
     forehead
    1.74
     shoulders
    1.62
     chest
    1.62
     neck
    1.58
     abdomen
    1.55
     cheeks
    1.53
     thighs
    1.52
     chin
    1.50
     buttocks
    1.49
     lips
    1.48
    Activations Density 0.129%

    No Known Activations