© 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. 9982
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to computer programming and technical configurations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to group or event identifiers, often in a gaming or entertainment context

    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
     laun
    -0.93
    anish
    -0.86
    cffff
    -0.81
    hare
    -0.78
     satell
    -0.78
    kefeller
    -0.73
     resil
    -0.73
    ahu
    -0.72
    ingu
    -0.70
    soft
    -0.70
    POSITIVE LOGITS
     Chapter
    1.32
     Pt
    1.32
     Section
    1.21
    Chapter
    1.21
    Section
    1.20
     Part
    1.17
     Chapters
    1.14
     Episode
    1.14
     Sections
    1.07
    APTER
    1.06
    Activations Density 0.322%

    No Known Activations