© 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. 4-RES-JB
    11. 516
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or locations related to finance or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to Wall Street

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

    No Comments

    Negative Logits
    lihood
    -0.94
    netflix
    -0.79
    ãģ¦
    -0.75
    esthetic
    -0.72
     Carbuncle
    -0.72
    milo
    -0.71
    £ı
    -0.67
    hift
    -0.66
    Ļ½
    -0.66
    orate
    -0.65
    POSITIVE LOGITS
    abies
    1.25
    papers
    1.24
    paper
    1.07
    aby
    0.90
    banks
    0.88
     Wall
    0.79
    anke
    0.79
    ahs
    0.78
    itzer
    0.77
    iday
    0.77
    Activations Density 0.011%

    No Known Activations