© 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. 412
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe characteristics of products or concepts

    oai_token-act-pair · gpt-3.5-turbo

    sequential adjectives describing various qualities and characteristics

    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
    vation
    -0.85
    EStream
    -0.83
    Forge
    -0.75
    EMENT
    -0.73
    swick
    -0.73
    asio
    -0.73
    ulla
    -0.73
    ipation
    -0.70
    SHIP
    -0.70
    regation
    -0.68
    POSITIVE LOGITS
     albeit
    0.96
     but
    0.88
     whereas
    0.85
     resilient
    0.82
     though
    0.82
     although
    0.81
     ie
    0.80
     however
    0.79
     technologically
    0.78
     efficient
    0.78
    Activations Density 0.237%

    No Known Activations