© 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. 4-RES-JB
    11. 20256
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to various events and locations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations, events, or programs

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

    No Comments

    Negative Logits
     Diaz
    -0.67
    kson
    -0.62
    cean
    -0.60
     Moz
    -0.59
     Winchester
    -0.59
     Britann
    -0.58
     Romania
    -0.58
     Gamb
    -0.57
     Sax
    -0.57
     shore
    -0.56
    POSITIVE LOGITS
    ET
    1.22
    INE
    1.19
    ILE
    1.17
    ILL
    1.14
    ELY
    1.13
    ARY
    1.13
    ON
    1.11
    ICH
    1.11
    ILLE
    1.10
    ISH
    1.10
    Activations Density 0.105%

    No Known Activations