© 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. 2-RES-JB
    11. 17427
    Prev
    Next
    INDEX
    Explanations

    questions ending with question marks

    oai_token-act-pair · gpt-3.5-turbo

    questions that prompt introspection or inquiry about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athe
    -0.71
    ridor
    -0.67
     encount
    -0.66
    itialized
    -0.66
    onds
    -0.65
     ankles
    -0.64
     glim
    -0.63
    aper
    -0.63
    aled
    -0.62
    eper
    -0.62
    POSITIVE LOGITS
     Surely
    0.95
     Wouldn
    0.93
     Nope
    0.90
     Why
    0.90
    .?
    0.89
     Certainly
    0.88
     Perhaps
    0.86
     What
    0.85
     Probably
    0.85
     Would
    0.84
    Activations Density 0.090%

    No Known Activations