© 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. 22254
    Prev
    Next
    INDEX
    Explanations

    operating system versions and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to operating system updates and software versions

    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
    agher
    -0.79
     purse
    -0.73
     Swanson
    -0.71
     laughter
    -0.69
     drown
    -0.68
     divers
    -0.67
     funeral
    -0.66
     anonymously
    -0.66
     calmly
    -0.66
     testim
    -0.65
    POSITIVE LOGITS
    Version
    1.22
     firmware
    1.20
    installed
    1.11
     compatibility
    1.10
     compatible
    1.09
     macOS
    1.07
     patched
    1.06
     Version
    1.05
     Compatibility
    1.01
     DirectX
    1.01
    Activations Density 0.489%

    No Known Activations