© 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. 20436
    Prev
    Next
    INDEX
    Explanations

    words related to online forms or prompts, such as "Enter"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Enter."

    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
    acca
    -0.70
    76561
    -0.69
     conviction
    -0.68
     coun
    -0.67
     backdrop
    -0.62
    ector
    -0.59
     laundering
    -0.59
     disposed
    -0.59
     sled
    -0.58
     Archangel
    -0.58
    POSITIVE LOGITS
    prise
    1.58
    prises
    1.56
    tainment
    1.40
    tain
    1.26
    prising
    1.21
    taining
    1.17
    tis
    0.90
    TAIN
    0.90
    tained
    0.84
    ipher
    0.83
    Activations Density 0.010%

    No Known Activations