© 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. 7745
    Prev
    Next
    INDEX
    Explanations

    references to questions or conversations that seek opinions or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate asking or referencing questions and discussions

    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
    soever
    -0.79
    anooga
    -0.77
    iren
    -0.73
    Frameworks
    -0.71
    à¼
    -0.68
    Ò
    -0.67
    ulum
    -0.67
    Ê
    -0.67
    seed
    -0.67
    %%
    -0.66
    POSITIVE LOGITS
     why
    1.18
     whether
    1.06
     how
    1.04
     his
    1.03
     wanting
    0.93
     possible
    0.91
     himself
    0.84
     rumors
    0.84
     allegations
    0.84
     rumours
    0.80
    Activations Density 0.268%

    No Known Activations