© 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. 11-RES-JB
    11. 6624
    Prev
    Next
    INDEX
    Explanations

    references to specific place names, especially cities

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or institutional entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.88
    ĻĤ
    -0.71
    iannopoulos
    -0.70
     traumatic
    -0.65
    furt
    -0.59
     paste
    -0.58
     relativity
    -0.58
    ĪĴ
    -0.57
     matt
    -0.56
    etting
    -0.55
    POSITIVE LOGITS
     Accountability
    1.05
     Of
    0.96
     Fathers
    0.96
     Builder
    0.92
     Council
    0.89
     Bureau
    0.87
     of
    0.86
     Himself
    0.84
     Commission
    0.84
     Committee
    0.83
    Activations Density 0.213%

    No Known Activations