© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    individuals with specific personal or professional attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to time intervals and significant events in people's lives

    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
    "!
    -0.65
     tremend
    -0.61
    apest
    -0.58
    idden
    -0.51
    ãĥij
    -0.50
    ãĤ³
    -0.49
     Subtle
    -0.49
    Orig
    -0.49
    ãĤ¢ãĥ«
    -0.48
     nodd
    -0.48
    POSITIVE LOGITS
    ?,
    0.96
    Downloadha
    0.83
    ,
    0.82
    ,[
    0.74
     says
    0.74
     ,
    0.73
    ,...
    0.72
     believes
    0.68
    })
    0.68
     admits
    0.68
    Activations Density 0.495%

    No Known Activations