© 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. 0-RES-JB
    11. 2533
    Prev
    Next
    INDEX
    Explanations

    names or references to "pizza"

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific individuals, particularly those in positions of power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desper
    -0.79
    cial
    -0.67
    oké
    -0.66
    adal
    -0.66
     Tac
    -0.66
     tribes
    -0.64
     Tem
    -0.63
    Balt
    -0.63
     Valhalla
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    POSITIVE LOGITS
     HE
    2.26
    zza
    1.92
    HE
    1.87
    ISA
    1.65
    ews
    1.03
    AME
    0.98
    ppings
    0.97
     microwave
    0.90
    ewski
    0.89
    iren
    0.87
    Activations Density 0.035%

    No Known Activations