© 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. 11-RES-JB
    11. 1250
    Prev
    Next
    INDEX
    Explanations

    names or acronyms related to various organizations or companies

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blur
    -0.64
     whis
    -0.64
    killers
    -0.64
    strings
    -0.63
    things
    -0.63
     awa
    -0.60
     saint
    -0.60
     identifiable
    -0.60
     guessing
    -0.59
     Caesar
    -0.58
    POSITIVE LOGITS
    IRE
    1.57
    UNE
    1.46
    KA
    1.43
    OOL
    1.42
    AN
    1.41
    ITE
    1.41
    IFE
    1.41
    ON
    1.40
    ICS
    1.39
    UTE
    1.39
    Activations Density 0.211%

    No Known Activations