© 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. 1-RES-JB
    11. 12094
    Prev
    Next
    INDEX
    Explanations

    references to the Everglades or locations with "Ever" in their name

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ever," suggesting a focus on time-related references or constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.84
    illary
    -0.74
    ologies
    -0.74
    ombat
    -0.73
    İĭ
    -0.71
    sym
    -0.68
    ypes
    -0.67
    illation
    -0.66
    ains
    -0.63
    ÃĥÃĤ
    -0.63
    POSITIVE LOGITS
    theless
    1.09
    deen
    0.95
    THING
    0.92
    lasting
    0.92
    leigh
    0.89
    agher
    0.85
    ton
    0.81
     EVER
    0.80
    thing
    0.79
    ever
    0.79
    Activations Density 0.004%

    No Known Activations