© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    titles or headings within text

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "MORE."

    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
    vet
    -0.79
    aper
    -0.79
    stood
    -0.78
    arist
    -0.78
    riber
    -0.76
    liest
    -0.74
    etime
    -0.72
    reen
    -0.71
    ibel
    -0.71
    ee
    -0.71
    POSITIVE LOGITS
    MORE
    1.13
    HEAD
    0.93
     than
    0.88
     ado
    0.86
    agascar
    0.83
    FTWARE
    0.79
     convol
    0.76
     VIDEOS
    0.76
     MORE
    0.76
     ABOUT
    0.74
    Activations Density 0.005%

    No Known Activations