© 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. 0-RES-JB
    11. 18852
    Prev
    Next
    INDEX
    Explanations

    words related to groups or categories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of quintiles in statistical distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Money
    -0.75
     Donkey
    -0.73
    asel
    -0.72
    ARE
    -0.71
    ousel
    -0.70
     Foley
    -0.70
    nels
    -0.70
     Doodle
    -0.68
     Beaver
    -0.67
     Lou
    -0.67
    POSITIVE LOGITS
     quint
    3.16
     Quint
    2.70
     quart
    2.54
     Quart
    1.99
    quart
    1.64
     tert
    1.30
     Sax
    1.26
     virt
    1.19
    Sax
    1.15
     sax
    1.12
    Activations Density 0.036%

    No Known Activations