© 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. 4-RES-JB
    11. 6425
    Prev
    Next
    INDEX
    Explanations

    terms related to wealth, taxes, and web-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth, the internet, and environmental topics

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

    No Comments

    Negative Logits
    Sov
    -0.78
    tein
    -0.75
    Prof
    -0.67
    ittees
    -0.65
    pec
    -0.64
     Vill
    -0.62
    BuyableInstoreAndOnline
    -0.62
    å¦
    -0.62
    Det
    -0.62
    Fac
    -0.61
    POSITIVE LOGITS
    osphere
    0.85
    isphere
    0.75
    ousel
    0.71
    leigh
    0.70
    waves
    0.69
     itself
    0.68
    iets
    0.68
    isp
    0.68
    liest
    0.67
    lings
    0.65
    Activations Density 0.429%

    No Known Activations