© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    information on abundance or a large quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or emphasize abundance or plenty

    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
    acus
    -0.89
    ĸļ
    -0.86
    ħĭ
    -0.83
    most
    -0.83
    gypt
    -0.80
    acle
    -0.73
    externalActionCode
    -0.73
    ESE
    -0.72
    rust
    -0.70
    hani
    -0.70
    POSITIVE LOGITS
     opportunities
    0.94
     surprises
    0.88
     times
    0.84
     unanswered
    0.79
     juicy
    0.78
     occasions
    0.77
     interesting
    0.76
     parallels
    0.76
     ammunition
    0.75
     caveats
    0.75
    Activations Density 0.054%

    No Known Activations