© 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. 10-RES-JB
    11. 4922
    Prev
    Next
    INDEX
    Explanations

    information about pharmaceuticals, chemicals, and their effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negative health implications or lack of medical value

    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
    ooter
    -0.75
     Franch
    -0.75
    Train
    -0.70
    Particip
    -0.69
    ©¶æ
    -0.69
    cember
    -0.68
     Attend
    -0.67
    ansas
    -0.66
    opolis
    -0.66
    Items
    -0.66
    POSITIVE LOGITS
     advantages
    1.22
     properties
    1.17
     characteristics
    1.15
     qualities
    1.08
     versatility
    1.08
     potency
    1.08
     drawbacks
    1.07
     usefulness
    1.06
     medicinal
    1.04
     durability
    1.04
    Activations Density 0.268%

    No Known Activations