© 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. 17122
    Prev
    Next
    INDEX
    Explanations

    symbols and text formatting such as bullets and arrows

    oai_token-act-pair · gpt-3.5-turbo

    symbols or indicators related to links, connections, and related web content management themes

    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
    opian
    -0.81
     strugg
    -0.74
     resent
    -0.69
     penal
    -0.69
    qus
    -0.68
    bage
    -0.68
     menstru
    -0.68
     Vaugh
    -0.67
    zon
    -0.67
     agre
    -0.66
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.91
     Featuring
    0.80
     Cosponsors
    0.77
     Allows
    0.76
     Various
    0.76
     Provides
    0.73
     âĺħ
    0.72
     à¤
    0.72
     Increases
    0.72
    ËĪ
    0.71
    Activations Density 0.307%

    No Known Activations