© 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. 3286
    Prev
    Next
    INDEX
    Explanations

    company names or abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    company names and identifiers

    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
    taboola
    -0.67
     ré
    -0.61
     surpr
    -0.59
     clutter
    -0.58
     speedy
    -0.58
     scientifically
    -0.57
     unpop
    -0.57
     raise
    -0.56
    thinkable
    -0.56
     perfect
    -0.56
    POSITIVE LOGITS
    FU
    1.00
    HY
    0.97
    KI
    0.97
    KA
    0.95
    BG
    0.91
    HE
    0.90
    KO
    0.89
    ZA
    0.88
    KT
    0.88
    IU
    0.87
    Activations Density 0.154%

    No Known Activations