© 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. 6-RES-JB
    11. 14761
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    connections between various people, entities, and actions in a complex narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lynn
    -0.57
     Ranked
    -0.55
     Rooney
    -0.54
     Starr
    -0.54
     Ashe
    -0.54
     Lynch
    -0.53
     Entered
    -0.53
     Rutherford
    -0.52
     trout
    -0.52
     chimpan
    -0.51
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.76
    ãģ®ç
    0.73
    edIn
    0.72
    orem
    0.70
    ļéĨĴ
    0.69
    ĵĺ
    0.68
    ragon
    0.65
    oxide
    0.65
    ãģ®é
    0.65
    yond
    0.64
    Activations Density 1.083%

    No Known Activations