© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21251
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large amount or quantity

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases emphasizing quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.90
    ĸļ
    -0.82
    acus
    -0.81
    atis
    -0.78
    usp
    -0.74
    ule
    -0.74
    ful
    -0.73
    ĪĴ
    -0.71
    gypt
    -0.69
    acle
    -0.68
    POSITIVE LOGITS
     times
    0.92
     things
    0.85
     fun
    0.84
     interesting
    0.81
     mileage
    0.78
     unanswered
    0.76
     misinformation
    0.75
     money
    0.75
     variability
    0.74
     stuff
    0.73
    Activations Density 0.086%

    No Known Activations