© 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 EvalsExportsinterp-engineNEWAPI 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. 11842
    Prev
    Next
    INDEX
    Explanations

    keywords in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive gaming or scoring systems

    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
     Sapp
    -0.74
     scram
    -0.71
     Regist
    -0.69
     ILCS
    -0.65
     acceler
    -0.63
     Stub
    -0.63
     Saras
    -0.63
    lycer
    -0.62
     Lumpur
    -0.62
     resear
    -0.62
    POSITIVE LOGITS
    Secondly
    0.99
    VII
    0.89
    ii
    0.86
    II
    0.84
     secondly
    0.82
    III
    0.77
     ii
    0.77
    iii
    0.76
    ¾
    0.75
    Solution
    0.75
    Activations Density 0.637%

    No Known Activations