© 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. 1-RES-JB
    11. 14360
    Prev
    Next
    INDEX
    Explanations

    uppercase abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to frameworks or specifications, particularly in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.77
    holder
    -0.74
     PsyNet
    -0.73
    gow
    -0.72
     Totem
    -0.66
     Tsu
    -0.66
    ulet
    -0.65
    lace
    -0.65
     Hiroshima
    -0.64
     Dragonbound
    -0.63
    POSITIVE LOGITS
    ONT
    1.26
    ugal
    1.11
    FR
    0.98
    ESH
    0.97
    andom
    0.92
    AME
    0.89
    owship
    0.88
    iggs
    0.86
    ANCE
    0.81
    ACTION
    0.80
    Activations Density 0.007%

    No Known Activations