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

    Neuronpedia

    Jacobian LensNEW
    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. 16529
    Prev
    Next
    INDEX
    Explanations

    single words containing the substring "ub"

    oai_token-act-pair · gpt-3.5-turbo

    mentions related to the automobile brand Mitsubishi and its products

    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
     Lauder
    -0.74
     ozone
    -0.69
     ORIG
    -0.66
     drift
    -0.66
     cig
    -0.63
     Noir
    -0.62
     wart
    -0.61
     cigarette
    -0.59
     Irma
    -0.59
     Burnett
    -0.57
    POSITIVE LOGITS
    lishing
    1.38
    bing
    1.27
    lish
    1.19
    lisher
    1.18
    rious
    1.12
    bed
    1.12
    bish
    1.12
    lique
    1.11
    bers
    1.04
    ilant
    1.02
    Activations Density 0.009%

    No Known Activations