© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6851
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical connectors and cables

    oai_token-act-pair · gpt-3.5-turbo

    technical information related to electronic device connectivity and components

    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
    sted
    -0.84
     Rankings
    -0.77
     Scholar
    -0.75
     judgments
    -0.75
     vulgar
    -0.74
    Population
    -0.73
    racial
    -0.70
     celebrations
    -0.70
    eries
    -0.69
     Brave
    -0.69
    POSITIVE LOGITS
     adapter
    1.37
     connector
    1.36
     connectors
    1.35
     removable
    1.32
     socket
    1.27
     wires
    1.26
     USB
    1.25
     sockets
    1.23
     Arduino
    1.22
     wiring
    1.22
    Activations Density 0.671%

    No Known Activations