© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5635
    Prev
    Next
    INDEX
    Explanations

    mentions of influential and iconic figures, especially in intellectual or cultural contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to influential thinkers and their notable contributions

    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
    artment
    -0.74
     Response
    -0.73
    Nusra
    -0.73
     prepaid
    -0.73
    IDA
    -0.71
     coord
    -0.71
     Setup
    -0.71
    Operation
    -0.71
    Defense
    -0.71
    aspx
    -0.70
    POSITIVE LOGITS
     contemporaries
    1.28
     seminal
    1.26
     classics
    1.21
     prolific
    1.21
     visionary
    1.20
     pioneering
    1.20
     legendary
    1.18
     revered
    1.16
     literary
    1.15
     pioneer
    1.13
    Activations Density 0.698%

    No Known Activations