© 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. 8-RES-JB
    11. 17597
    Prev
    Next
    INDEX
    Explanations

    references to movement from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of incidents or events

    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
    ople
    -0.69
     Moonlight
    -0.64
     Clubs
    -0.59
     Concord
    -0.59
     Registry
    -0.56
     Henri
    -0.55
     Scouts
    -0.55
     Leth
    -0.54
     Ajax
    -0.54
     widest
    -0.54
    POSITIVE LOGITS
    worldly
    1.03
    bender
    0.90
     besides
    0.82
    roller
    0.79
     than
    0.78
    mate
    0.76
    anche
    0.76
    than
    0.74
    ypes
    0.73
    cake
    0.72
    Activations Density 0.299%

    No Known Activations