© 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. 4-RES-JB
    11. 48
    Prev
    Next
    INDEX
    Explanations

    web URLs containing the word "pub" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "pub" and associated variations

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

    No Comments

    Negative Logits
     Isles
    -0.86
     Argent
    -0.77
     Esper
    -0.77
    IRD
    -0.76
     Bravo
    -0.76
    OHN
    -0.75
    BuyableInstoreAndOnline
    -0.75
     Spears
    -0.73
     ANGEL
    -0.73
     Daytona
    -0.72
    POSITIVE LOGITS
    lishing
    1.83
    lisher
    1.78
    lish
    1.39
    lishes
    1.34
    lique
    1.20
    escent
    1.14
    lished
    1.09
    lik
    0.99
    iled
    0.97
    ression
    0.95
    Activations Density 0.023%

    No Known Activations