© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    descriptions of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to technology specifications and performance

    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
     UNCLASSIFIED
    -0.76
    reporting
    -0.73
     discredited
    -0.68
     advis
    -0.66
     Democracy
    -0.66
    journal
    -0.65
     presidency
    -0.63
     Political
    -0.63
    Jews
    -0.62
     recount
    -0.62
    POSITIVE LOGITS
     versatility
    1.02
     customization
    0.95
     specs
    0.94
     ASUS
    0.91
     presets
    0.89
     Asus
    0.87
     versatile
    0.85
     removable
    0.85
     customizable
    0.84
     accessories
    0.84
    Activations Density 1.100%

    No Known Activations