© 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. 10-RES-JB
    11. 18630
    Prev
    Next
    INDEX
    Explanations

    web links and specific references embedded in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and information sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yugoslavia
    -0.56
     unforeseen
    -0.55
     exagger
    -0.54
     balk
    -0.54
     unintended
    -0.52
     Bai
    -0.52
    ordinate
    -0.52
    aunted
    -0.51
     forbid
    -0.51
    utters
    -0.50
    POSITIVE LOGITS
     HERE
    1.64
     below
    1.29
     here
    1.28
    https
    1.19
     http
    1.12
    http
    1.10
    below
    1.10
     https
    1.08
     www
    1.06
     online
    0.94
    Activations Density 0.550%

    No Known Activations