© 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. 8-RES-JB
    11. 11000
    Prev
    Next
    INDEX
    Explanations

    words related to giving or attending lectures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lecture" and its variations

    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
    odka
    -0.69
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    anking
    -0.66
    ansas
    -0.65
     ignition
    -0.64
     Scotia
    -0.61
     overboard
    -0.60
     homeland
    -0.60
    bably
    -0.60
     Rossi
    -0.59
    POSITIVE LOGITS
     Lect
    1.16
    ures
    1.10
    urer
    0.97
    ured
    0.93
    urers
    0.89
    ure
    0.89
    inar
    0.85
    gow
    0.85
    shire
    0.84
    itle
    0.83
    Activations Density 0.022%

    No Known Activations