© 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. 22283
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific entities or concepts, such as names of places, institutions, and professions

    oai_token-act-pair · gpt-3.5-turbo

    specific names and titles of entities or organizations

    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
    ttes
    -0.66
     seiz
    -0.62
     rul
    -0.61
    rique
    -0.59
     skelet
    -0.56
     nodd
    -0.56
    tics
    -0.54
    ridges
    -0.53
    inous
    -0.52
    adder
    -0.49
    POSITIVE LOGITS
    ospons
    0.61
    !--
    0.59
    ADVERTISEMENT
    0.55
     guiActiveUn
    0.52
    ULTS
    0.52
    Enlarge
    0.52
    âĢİ
    0.52
    ONSORED
    0.51
    >>\
    0.51
     Helpful
    0.51
    Activations Density 1.600%

    No Known Activations