© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22540
    Prev
    Next
    INDEX
    Explanations

    words related to numerical data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the word "the."

    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
    ,''
    -0.68
    âĢİ
    -0.64
    America
    -0.63
    watching
    -0.63
     Mormonism
    -0.62
    stocks
    -0.62
    cape
    -0.61
    Share
    -0.60
    bill
    -0.59
    sure
    -0.59
    POSITIVE LOGITS
     latter
    1.67
     remainder
    1.48
     rest
    1.25
     same
    1.16
     second
    1.04
     heaviest
    1.04
     smallest
    1.04
     weakest
    1.03
     final
    1.02
     corresponding
    1.01
    Activations Density 0.651%

    No Known Activations