© 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. 7-RES-JB
    11. 1765
    Prev
    Next
    INDEX
    Explanations

    web URLs and mentions of websites

    oai_token-act-pair · gpt-3.5-turbo

    URLs or references to websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grounding
    -0.88
     uphill
    -0.81
     stride
    -0.78
     reception
    -0.77
     tides
    -0.77
     rooting
    -0.76
     tide
    -0.75
     turnout
    -0.73
     overlooked
    -0.72
     scaling
    -0.71
    POSITIVE LOGITS
    blogspot
    1.59
    wordpress
    1.56
    com
    1.43
    yahoo
    1.42
    tumblr
    1.41
    gmail
    1.34
    org
    1.32
    php
    1.23
    dll
    1.18
    htm
    1.17
    Activations Density 0.104%

    No Known Activations