© 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. 17623
    Prev
    Next
    INDEX
    Explanations

    environments and conditions, especially focusing on the structured settings and complex scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental contexts and conditions

    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
    ameless
    -0.64
    Compan
    -0.64
    named
    -0.64
    minster
    -0.64
    john
    -0.62
    arag
    -0.62
    aeper
    -0.61
    trak
    -0.61
    escription
    -0.61
    yright
    -0.61
    POSITIVE LOGITS
     (>
    0.97
     situations
    0.93
     environments
    0.90
     involving
    0.87
     alike
    0.86
     contexts
    0.80
     such
    0.78
     where
    0.78
     imaginable
    0.78
     (<
    0.78
    Activations Density 0.390%

    No Known Activations