© 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. 7043
    Prev
    Next
    INDEX
    Explanations

    quantifiers indicating the amount or extent of knowledge or information about a subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating varying degrees of knowledge or understanding

    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
     towed
    -0.61
    OPA
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.58
     pend
    -0.56
    wagon
    -0.55
    hement
    -0.55
    uga
    -0.55
    cled
    -0.55
     patronage
    -0.55
    issance
    -0.55
    POSITIVE LOGITS
     about
    0.93
     ABOUT
    0.89
     truths
    0.87
    about
    0.82
    omething
    0.77
     firsthand
    0.77
     details
    0.76
     beforehand
    0.76
     About
    0.73
     detail
    0.72
    Activations Density 0.209%

    No Known Activations