© 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. 6277
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons or approximations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate approximate quantities or statistics

    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
    Characters
    -0.72
    Sent
    -0.69
    ose
    -0.68
    actions
    -0.66
     deed
    -0.65
     POV
    -0.64
     deeds
    -0.63
     bearer
    -0.63
    aders
    -0.62
    ocy
    -0.62
    POSITIVE LOGITS
     560
    0.87
     580
    0.86
     tripled
    0.85
     twice
    0.83
     380
    0.83
     doubled
    0.81
     370
    0.80
     260
    0.80
     670
    0.79
     450
    0.78
    Activations Density 0.123%

    No Known Activations