© 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 EvalsExportsinterp-engineNEWAPI 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. 18911
    Prev
    Next
    INDEX
    Explanations

    information regarding investigations or disclosures involving the bodies of individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to possession or belonging

    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
    wcsstore
    -0.96
    iasm
    -0.85
    NetMessage
    -0.77
    >(
    -0.74
    wark
    -0.73
    é¾įåĸļ士
    -0.72
    dayName
    -0.72
    fax
    -0.72
    ãĥķãĤ©
    -0.72
    ucci
    -0.71
    POSITIVE LOGITS
     individuals
    1.25
     millions
    1.18
     countless
    1.13
     strangers
    1.13
     passers
    1.11
     those
    1.09
     unsuspecting
    1.09
     citizens
    1.08
     victims
    1.07
     deceased
    1.06
    Activations Density 0.200%

    No Known Activations