© 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. 17120
    Prev
    Next
    INDEX
    Explanations

    URL links

    oai_token-act-pair · gpt-3.5-turbo

    URLs and hyperlinks within the text

    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
    ricular
    -0.68
     overshadow
    -0.66
     unsus
    -0.65
    cffff
    -0.64
     Palest
    -0.64
     abst
    -0.63
     expulsion
    -0.62
    rons
    -0.62
     tremend
    -0.60
     Malt
    -0.59
    POSITIVE LOGITS
    ://
    1.65
    www
    1.16
     www
    1.00
    geist
    0.93
    :/
    0.91
    link
    0.86
    natureconservancy
    0.86
    doi
    0.82
    ww
    0.78
    web
    0.77
    Activations Density 0.013%

    No Known Activations