© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    words related to stamps and stamping

    oai_token-act-pair · gpt-3.5-turbo

    references to stamps and postage-related terms

    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
    izons
    -0.84
     Kut
    -0.78
    itably
    -0.73
    bid
    -0.72
    apist
    -0.71
    SOURCE
    -0.69
    anges
    -0.67
    odka
    -0.67
    ctory
    -0.67
    SE
    -0.67
    POSITIVE LOGITS
    eding
    1.17
     stamp
    0.89
     stamps
    0.89
    eed
    0.78
     collectors
    0.76
    ing
    0.76
    itious
    0.75
     collector
    0.74
    arding
    0.74
    pee
    0.74
    Activations Density 0.033%

    No Known Activations