© 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. 8-RES-JB
    11. 4263
    Prev
    Next
    INDEX
    Explanations

    names or aliases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks, often signaling direct quotes or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.75
    artifacts
    -0.73
    alysed
    -0.73
    align
    -0.72
    knit
    -0.72
    cffffcc
    -0.71
    uggest
    -0.70
     apex
    -0.69
     coincide
    -0.68
    =>
    -0.68
    POSITIVE LOGITS
     Andersen
    1.10
     Roberts
    1.06
     Johnson
    1.06
     Robinson
    1.00
     Mang
    0.98
     Rivera
    0.97
     Rivers
    0.96
     Wu
    0.96
     Dug
    0.96
     Sch
    0.95
    Activations Density 0.075%

    No Known Activations