© 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. 8-RES-JB
    11. 2182
    Prev
    Next
    INDEX
    Explanations

    keywords related to data or document requests, especially those involving legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to formal requests for information, specifically FOIA requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasses
    -0.82
    VERTISEMENT
    -0.79
    urst
    -0.69
    nat
    -0.69
    olson
    -0.66
    heartedly
    -0.66
    shock
    -0.65
     Blacks
    -0.64
    icals
    -0.63
    stocks
    -0.63
    POSITIVE LOGITS
     permission
    0.98
    Animation
    0.91
     requests
    0.89
     pardon
    0.85
     forgiveness
    0.80
     request
    0.78
     requested
    0.76
    irection
    0.74
    rison
    0.73
     warrants
    0.73
    Activations Density 0.040%

    No Known Activations