© 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. 0-RES-JB
    11. 6465
    Prev
    Next
    INDEX
    Explanations

    numeric codes or abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    references to "AT" as a critical acronym or abbreviation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.69
     Graves
    -0.68
     Xi
    -0.63
     peas
    -0.62
     Gerrard
    -0.61
     curtains
    -0.60
     fringe
    -0.60
     spills
    -0.60
    minster
    -0.60
     knight
    -0.60
    POSITIVE LOGITS
    AT
    4.00
    ATS
    2.53
    ATA
    1.93
    ats
    1.84
    ATT
    1.73
    ATING
    1.72
    ATOR
    1.70
     AT
    1.67
    ATER
    1.63
    ATE
    1.63
    Activations Density 0.008%

    No Known Activations