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

    Neuronpedia

    Jacobian LensNEW
    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. 10326
    Prev
    Next
    INDEX
    Explanations

    keywords related to digital technology and devices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital technology and devices

    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
     Avenger
    -0.75
     Conclusion
    -0.74
    origin
    -0.69
     Ambrose
    -0.66
     Destination
    -0.63
     Alban
    -0.63
    flags
    -0.62
     Sop
    -0.60
    Flags
    -0.59
     Virtue
    -0.58
    POSITIVE LOGITS
     savvy
    0.81
    sonian
    0.81
     screens
    0.80
     glitch
    0.74
    dating
    0.74
     kios
    0.73
    printed
    0.72
     cellphone
    0.72
     analytics
    0.71
     phones
    0.70
    Activations Density 0.448%

    No Known Activations