© 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. 18629
    Prev
    Next
    INDEX
    Explanations

    adjectives describing intensity or severity

    oai_token-act-pair · gpt-3.5-turbo

    terms describing mildness or pleasantness

    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
    aucus
    -0.67
     Accountability
    -0.66
    hedral
    -0.66
    rencies
    -0.65
    lining
    -0.64
    aturated
    -0.63
    ilings
    -0.62
    funding
    -0.60
    etus
    -0.60
     Emir
    -0.60
    POSITIVE LOGITS
    hello
    0.79
     harmless
    0.78
     annoyance
    0.77
     surprise
    0.76
     surprises
    0.75
     nuisance
    0.75
    »Ĵ
    0.75
     surpr
    0.73
    ew
    0.71
     prank
    0.70
    Activations Density 0.091%

    No Known Activations