© 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. 9-RES-JB
    11. 3278
    Prev
    Next
    INDEX
    Explanations

    mentions about interaction or collaboration between individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of interactions or collaborations between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.86
    zbollah
    -0.84
    opsis
    -0.80
    Picture
    -0.76
     APPLIC
    -0.76
    avascript
    -0.76
    yrim
    -0.74
    Israeli
    -0.71
    inav
    -0.69
    ancial
    -0.69
    POSITIVE LOGITS
     him
    1.12
     Jacobs
    1.06
     Hernandez
    1.00
     Michaels
    0.99
     Fowler
    0.99
     Rivera
    0.99
     Payne
    0.99
     Ortiz
    0.98
     Ellison
    0.98
     Gillespie
    0.97
    Activations Density 1.670%

    No Known Activations