© 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. 18552
    Prev
    Next
    INDEX
    Explanations

    words prefixed with "in-" or phrases that could relate to something internal or inherent to a situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "in-depth."

    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
    Ń·
    -0.71
    illac
    -0.70
     Reloaded
    -0.66
     Blues
    -0.64
     Hoo
    -0.64
     DOI
    -0.59
     Chero
    -0.59
    Ĥª
    -0.59
     Kuh
    -0.59
     Doodle
    -0.58
    POSITIVE LOGITS
    depth
    1.17
    advert
    1.09
    built
    1.07
    line
    1.05
    sight
    1.03
    development
    1.02
    camera
    1.00
    browser
    1.00
    bet
    0.97
    between
    0.95
    Activations Density 0.028%

    No Known Activations