© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17203
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical changes

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to changes in various measurements or proportions

    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
     Dish
    -0.76
     dishes
    -0.75
     Mour
    -0.74
     Ago
    -0.68
     dish
    -0.67
     latch
    -0.66
    rique
    -0.65
     Mast
    -0.64
     Offer
    -0.63
     Franch
    -0.63
    POSITIVE LOGITS
     fluct
    1.03
     tripled
    0.96
     exceeded
    0.93
     negligible
    0.90
     exceed
    0.90
     varied
    0.89
     doubled
    0.88
     quadru
    0.87
     overest
    0.85
    higher
    0.84
    Activations Density 0.386%

    No Known Activations