© 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. 9-RES-JB
    11. 13978
    Prev
    Next
    INDEX
    Explanations

    words related to renowned individuals or public figures

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or patterns related to individuals' names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olves
    -0.75
    ultimate
    -0.63
    ror
    -0.63
    ocalypse
    -0.63
    othal
    -0.61
    ocry
    -0.61
    feed
    -0.61
    alysis
    -0.61
    akedown
    -0.61
    atile
    -0.60
    POSITIVE LOGITS
     meanwhile
    1.11
     whose
    1.08
     however
    1.06
    whose
    1.04
     who
    1.02
     flanked
    1.00
     nicknamed
    0.94
     along
    0.93
    who
    0.93
     pictured
    0.90
    Activations Density 0.161%

    No Known Activations