© 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. 24072
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and updates

    oai_token-act-pair · gpt-3.5-turbo

    references to a company and its products or services

    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
    hari
    -0.91
    lehem
    -0.85
    nin
    -0.79
    Filename
    -0.79
    orgetown
    -0.78
    skirts
    -0.77
    tale
    -0.76
    olkien
    -0.76
    iece
    -0.74
    icter
    -0.74
    POSITIVE LOGITS
     own
    1.48
     flagship
    1.26
     proprietary
    1.22
     products
    1.13
     competitors
    1.13
     patented
    1.10
     subsidiaries
    1.09
     customers
    1.07
     subsidiary
    1.04
     newest
    1.03
    Activations Density 0.305%

    No Known Activations