© 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. 3-RES-JB
    11. 6132
    Prev
    Next
    INDEX
    Explanations

    web URLs or references in the form of "uv" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to UV (ultraviolet) light or related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -0.75
    ndra
    -0.75
    IZE
    -0.70
    quarters
    -0.68
    cone
    -0.65
     Carnival
    -0.65
    venture
    -0.65
     Solitaire
    -0.61
    insula
    -0.61
     fingers
    -0.60
    POSITIVE LOGITS
    rolet
    1.16
    uv
    0.91
    ibe
    0.86
    riel
    0.86
    ados
    0.83
    rons
    0.82
    inators
    0.79
    ois
    0.78
    adia
    0.78
    idge
    0.76
    Activations Density 0.005%

    No Known Activations