© 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. 0-RES-JB
    11. 8152
    Prev
    Next
    INDEX
    Explanations

    the word "ELL" at high activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "yellowstone" and its variations, along with mentions of "tut" and "stem"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.82
    iously
    -0.70
    ance
    -0.70
    ious
    -0.69
     Bis
    -0.65
    owship
    -0.64
    atus
    -0.63
     Bene
    -0.63
    bis
    -0.62
    ateur
    -0.61
    POSITIVE LOGITS
    ELL
    4.21
     tut
    1.42
    EAR
    1.04
     tutor
    1.03
    alam
    1.01
    tty
    0.92
    stem
    0.90
    EV
    0.83
    ugi
    0.82
    elli
    0.79
    Activations Density 0.037%

    No Known Activations