© 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. 6-RES-JB
    11. 392
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific place or person named "Scott"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and locations related to a story or event

    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
    CVE
    -0.76
     CTR
    -0.68
    ives
    -0.65
     livest
    -0.62
    ¥ŀ
    -0.62
     thence
    -0.59
    ACTED
    -0.58
     Mae
    -0.57
    DIV
    -0.57
    200000
    -0.56
    POSITIVE LOGITS
    ty
    1.01
    cone
    0.96
    mingham
    0.90
    Rail
    0.90
     Scot
    0.89
    acular
    0.88
    Scot
    0.87
    ters
    0.86
    enos
    0.86
    kered
    0.85
    Activations Density 0.029%

    No Known Activations