© 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. 4-RES-JB
    11. 4824
    Prev
    Next
    INDEX
    Explanations

    references or mentions of logging in or being logged in

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "logged" and its variations related to accounts and access

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

    No Comments

    Negative Logits
    silver
    -0.69
    xual
    -0.65
    nces
    -0.63
    riages
    -0.62
    anus
    -0.61
     Boris
    -0.61
    ners
    -0.59
    atown
    -0.59
    hhhh
    -0.58
    hhh
    -0.58
    POSITIVE LOGITS
    gers
    1.05
    istically
    1.02
     logs
    0.96
    istics
    0.90
    ophon
    0.88
    istical
    0.84
    ging
    0.84
     logger
    0.82
    opers
    0.81
    otype
    0.81
    Activations Density 0.008%

    No Known Activations