© 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. 2-RES-JB
    11. 11676
    Prev
    Next
    INDEX
    Explanations

    capitalized words or proper nouns related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "OT" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixme
    -0.70
     sinks
    -0.62
    plain
    -0.61
     waters
    -0.60
     Verd
    -0.59
    ãĥĭ
    -0.59
     Thur
    -0.58
    kers
    -0.58
    bler
    -0.57
     Michaels
    -0.57
    POSITIVE LOGITS
    OT
    1.22
    assium
    1.03
    OGR
    1.00
    ICAN
    0.98
    TE
    0.97
    TL
    0.97
    inyl
    0.95
    IC
    0.94
    oot
    0.94
    YP
    0.91
    Activations Density 0.005%

    No Known Activations