© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    issues or errors prompting a request to try again later

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of errors and the need to try again later

    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
    roots
    -0.82
    quartered
    -0.80
    ³³³³³³³³³³³³³³³³
    -0.80
    Extreme
    -0.73
    ³³³³³³³³
    -0.69
    etts
    -0.67
    mong
    -0.66
    laws
    -0.65
    abal
    -0.65
    paces
    -0.65
    POSITIVE LOGITS
     Cancel
    0.69
     delete
    0.69
     disable
    0.69
     cancel
    0.67
     upload
    0.65
     login
    0.64
     captcha
    0.63
     VPN
    0.62
     disembark
    0.61
     overdoses
    0.61
    Activations Density 0.018%

    No Known Activations