© 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. 8-RES-JB
    11. 7023
    Prev
    Next
    INDEX
    Explanations

    scientific terms or phrases related to chemistry and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "A" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incompet
    -0.71
    aneously
    -0.68
    arsity
    -0.65
     honors
    -0.64
     sights
    -0.63
    !!!!
    -0.61
     Legions
    -0.60
     Oprah
    -0.58
     Orient
    -0.58
     Elvis
    -0.58
    POSITIVE LOGITS
    cknowled
    1.28
    cknow
    1.24
    verages
    1.16
    ctions
    1.13
     typical
    1.13
     drawback
    1.03
     lot
    1.01
    ctors
    0.96
    chie
    0.96
     downside
    0.95
    Activations Density 0.151%

    No Known Activations