© 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. 17118
    Prev
    Next
    INDEX
    Explanations

    terms related to machinery and machinations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanics and engineering processes

    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
    blank
    -0.73
    DragonMagazine
    -0.73
    HCR
    -0.72
     Supplement
    -0.70
    PORT
    -0.68
    hyde
    -0.68
    kj
    -0.66
    BUG
    -0.66
    lihood
    -0.65
    aiman
    -0.64
    POSITIVE LOGITS
     mach
    1.06
    inations
    1.02
    ineries
    0.91
    azi
    0.88
    ining
    0.83
    ined
    0.82
     corrid
    0.82
    otomy
    0.81
    eers
    0.80
    imet
    0.78
    Activations Density 0.008%

    No Known Activations