© 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. 6-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    people or groups of people that someone has spoken to

    oai_token-act-pair · gpt-3.5-turbo

    references to people or groups involved in discussions or interviews

    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
     phased
    -0.63
     prev
    -0.63
     spans
    -0.61
     millennium
    -0.61
    Pg
    -0.60
     consumed
    -0.60
     largeDownload
    -0.59
     depended
    -0.59
     irrad
    -0.58
     bets
    -0.58
    POSITIVE LOGITS
     representatives
    0.79
    omever
    0.78
     interviewer
    0.71
     Slack
    0.69
     recru
    0.68
    uli
    0.68
    HQ
    0.67
    orters
    0.65
    strate
    0.65
    mbuds
    0.64
    Activations Density 0.644%

    No Known Activations