© 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. 7-RES-JB
    11. 12441
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "spin"

    oai_token-act-pair · gpt-3.5-turbo

    references to spin-offs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ermott
    -0.68
    inez
    -0.67
     LIA
    -0.63
    inances
    -0.61
    avis
    -0.61
     Admir
    -0.61
     stakes
    -0.60
     Territories
    -0.58
     Defenders
    -0.58
    anan
    -0.58
    POSITIVE LOGITS
    ners
    1.43
    eless
    0.93
    kered
    0.93
     spin
    0.90
    ned
    0.88
    offs
    0.87
    wheel
    0.86
    lass
    0.85
    ball
    0.85
     yarn
    0.84
    Activations Density 0.028%

    No Known Activations