© 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. 8-RES-JB
    11. 10864
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contrast or comparison in performance or quality

    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
    vernment
    -0.92
    âĢİ
    -0.79
     Rodham
    -0.78
     Tours
    -0.73
     President
    -0.71
     Tomorrow
    -0.71
    meet
    -0.70
     Presidents
    -0.68
    Washington
    -0.68
     Mitt
    -0.67
    POSITIVE LOGITS
     negligible
    1.16
     decrease
    1.01
     thickness
    1.00
     offset
    1.00
     amplitude
    0.98
     gradient
    0.97
     offsets
    0.96
     decreases
    0.95
     noticeable
    0.95
     saturation
    0.94
    Activations Density 0.924%

    No Known Activations