© 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. 9-RES-JB
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    words related to coverage or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scope and coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onew
    -0.71
    inx
    -0.70
    bra
    -0.69
    æ°
    -0.69
    inem
    -0.69
    sie
    -0.68
    hook
    -0.68
    fml
    -0.65
    leen
    -0.64
    bell
    -0.63
    POSITIVE LOGITS
     both
    0.91
     everything
    0.88
     multiple
    0.87
     many
    0.82
     several
    0.82
     dozens
    0.81
     mainly
    0.81
     various
    0.80
     individuals
    0.78
     aspects
    0.78
    Activations Density 0.341%

    No Known Activations