© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 994
    Prev
    Next
    INDEX
    Explanations

    superlatives and adjectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing product quality and performance

    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
    ļéĨĴ
    -0.72
    iries
    -0.70
    ailed
    -0.70
    urden
    -0.70
    */(
    -0.69
    rahim
    -0.68
    alia
    -0.68
    zzle
    -0.67
    groups
    -0.65
     worries
    -0.65
    POSITIVE LOGITS
     culmination
    0.97
     flagship
    0.96
     standalone
    0.93
     masterpiece
    0.90
     gateway
    0.88
     classic
    0.87
     versatile
    0.87
     premiere
    0.86
     timeless
    0.84
     perfect
    0.84
    Activations Density 0.371%

    No Known Activations