© 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. 10-RES-JB
    11. 8277
    Prev
    Next
    INDEX
    Explanations

    words related to data processing or document formatting

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to loss or absence, particularly concerning marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ripple
    -0.95
     wrinkles
    -0.84
     flourish
    -0.81
     choke
    -0.78
     chants
    -0.76
     Torrent
    -0.75
     envy
    -0.75
     substitutes
    -0.75
     foreseeable
    -0.75
     tabloid
    -0.75
    POSITIVE LOGITS
    acqu
    1.34
    the
    1.32
    Great
    1.30
    Ap
    1.29
    great
    1.29
    Super
    1.28
    Commun
    1.28
    const
    1.28
    Internet
    1.26
    super
    1.26
    Activations Density 0.304%

    No Known Activations