© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 2486
    Prev
    Next
    INDEX
    Explanations

    terms related to effectiveness and success

    oai_token-act-pair · gpt-3.5-turbo

    terms related to effectiveness and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OWN
    -0.77
     Doodle
    -0.75
     Danger
    -0.74
    pper
    -0.73
    hyde
    -0.70
     Denmark
    -0.66
     Feld
    -0.65
    kson
    -0.64
     Roosevelt
    -0.64
     TAMADRA
    -0.64
    POSITIVE LOGITS
    iencies
    1.22
    sburgh
    0.89
    iveness
    0.88
     confir
    0.88
     effic
    0.87
     compr
    0.85
    ivity
    0.85
    umbnails
    0.85
    ency
    0.83
    iances
    0.83
    Activations Density 0.012%

    No Known Activations