© 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. 22266
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "W", potentially related to a range of topics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific abbreviations or initialisms, particularly related to organizations or entities

    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
    ptin
    -0.72
    rawdownloadcloneembedreportprint
    -0.69
    ãĤ©
    -0.67
    Tele
    -0.60
    --------------------------------------------------------
    -0.60
    uphem
    -0.58
    enegger
    -0.57
    ãĥĸ
    -0.57
    required
    -0.56
     compan
    -0.56
    POSITIVE LOGITS
    OPS
    0.95
    USH
    0.74
    TP
    0.67
    DF
    0.67
    ZI
    0.67
    KA
    0.66
    OP
    0.66
    IDA
    0.65
    AMS
    0.63
    ENSE
    0.61
    Activations Density 0.114%

    No Known Activations