© 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. 6-RES-JB
    11. 1486
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and technical topics

    oai_token-act-pair · gpt-3.5-turbo

    references to media content or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imperson
    -0.52
    soever
    -0.51
     joke
    -0.50
     sap
    -0.48
     bothered
    -0.48
     indirectly
    -0.48
     grate
    -0.47
     neglig
    -0.47
     reciproc
    -0.47
     mas
    -0.46
    POSITIVE LOGITS
    AUT
    0.58
     Catalyst
    0.50
     DISTRICT
    0.49
     Millenn
    0.48
     Murdoch
    0.47
    akra
    0.46
    natureconservancy
    0.46
    Options
    0.46
     Directions
    0.46
     ASUS
    0.45
    Activations Density 1.726%

    No Known Activations