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

    Neuronpedia

    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. 0-RES-JB
    11. 9535
    Prev
    Next
    INDEX
    Explanations

    text related to submitting documents or applications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "submitted" or variations of it

    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
    aund
    -0.67
    mop
    -0.67
    ppo
    -0.64
    gest
    -0.64
    omething
    -0.63
    wart
    -0.62
    lux
    -0.61
     Normandy
    -0.61
    ount
    -0.61
    lift
    -0.60
    POSITIVE LOGITS
     submitted
    3.41
     submit
    2.09
     submission
    2.06
     submissions
    2.05
     submitting
    1.91
     uploaded
    1.80
     Submission
    1.70
     filed
    1.69
     Submit
    1.47
     requested
    1.42
    Activations Density 0.005%

    No Known Activations