© 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. 15504
    Prev
    Next
    INDEX
    Explanations

    economic and demographic statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic trends and disparities

    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
    ensor
    -0.70
    iven
    -0.66
     Collider
    -0.65
    oggle
    -0.65
    ãĥ¯ãĥ³
    -0.64
     shroud
    -0.63
    Haunted
    -0.61
    DragonMagazine
    -0.61
     Clockwork
    -0.61
     godd
    -0.61
    POSITIVE LOGITS
     majorities
    1.06
     Percentage
    1.03
     median
    1.03
     Median
    1.02
    Percent
    1.02
    Average
    0.99
     Differences
    0.95
     Compared
    0.94
     prevalence
    0.92
     decreases
    0.92
    Activations Density 0.465%

    No Known Activations