© 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. 8-RES-JB
    11. 23809
    Prev
    Next
    INDEX
    Explanations

    references to the name "Nora" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dora" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.91
    ty
    -0.86
    ivity
    -0.84
    ELL
    -0.82
    leness
    -0.81
    fully
    -0.80
    ted
    -0.79
    ling
    -0.78
    zon
    -0.78
    ly
    -0.77
    POSITIVE LOGITS
     tremend
    0.79
    velength
    0.75
    uthor
    0.68
    Magazine
    0.67
    cffffcc
    0.67
     Austral
    0.64
    MpServer
    0.63
    ŃĶ
    0.63
     mund
    0.63
     bore
    0.63
    Activations Density 0.133%

    No Known Activations