© 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. 10-RES-JB
    11. 1456
    Prev
    Next
    INDEX
    Explanations

    political and professional titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles associated with leadership or decision-making positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.76
    thodox
    -0.75
    EStreamFrame
    -0.72
    illet
    -0.67
    illance
    -0.67
    uggle
    -0.67
     Marketable
    -0.64
    kus
    -0.64
    wagen
    -0.63
    ungle
    -0.61
    POSITIVE LOGITS
     Patrick
    1.18
     Stephen
    1.17
     Andrew
    1.17
     Jason
    1.15
     Michael
    1.13
     David
    1.13
     Robert
    1.12
     George
    1.12
     Timothy
    1.12
     Alan
    1.12
    Activations Density 0.179%

    No Known Activations