© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20124
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or terms, such as "MV," "Olsen," and "saturation."

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and terminology related to marine vessels and their impacts

    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
    Orig
    -0.84
    ERC
    -0.84
    hes
    -0.78
    DragonMagazine
    -0.77
    eport
    -0.76
    olph
    -0.74
    ribut
    -0.74
    itives
    -0.74
    ington
    -0.73
    hesis
    -0.69
    POSITIVE LOGITS
    rolet
    0.71
     iod
    0.71
    fleet
    0.70
     lapse
    0.69
     uptake
    0.68
     Faust
    0.68
     McCann
    0.67
     Lumpur
    0.65
    obyl
    0.64
     cohesion
    0.64
    Activations Density 0.021%

    No Known Activations