© 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. 11907
    Prev
    Next
    INDEX
    Explanations

    the surname "Bernanke"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of influential economic figures

    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
    itarian
    -0.92
    Lenin
    -0.72
    Ther
    -0.70
    FU
    -0.69
    ¥µ
    -0.66
     Kes
    -0.66
    Mich
    -0.65
     Ukrain
    -0.65
    pha
    -0.65
    amaz
    -0.64
    POSITIVE LOGITS
    anke
    0.86
    schild
    0.84
    affer
    0.75
    berries
    0.72
    agher
    0.68
    ucci
    0.67
    worms
    0.66
     Advis
    0.64
     outline
    0.63
     devised
    0.62
    Activations Density 0.047%

    No Known Activations