© 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. 6106
    Prev
    Next
    INDEX
    Explanations

    references to upcoming events or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to upcoming events or competitions

    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
     pseudonym
    -0.67
     prevailed
    -0.66
     contempor
    -0.66
    ographed
    -0.63
     stere
    -0.62
     Originally
    -0.61
    founded
    -0.61
     Changed
    -0.61
    emed
    -0.60
    rote
    -0.60
    POSITIVE LOGITS
     tomorrow
    1.14
     2019
    1.08
     next
    1.00
     showdown
    0.91
     2021
    0.90
     2018
    0.90
     finale
    0.88
     finals
    0.86
     festivities
    0.85
     recess
    0.85
    Activations Density 0.473%

    No Known Activations