© 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. 17360
    Prev
    Next
    INDEX
    Explanations

    references related to academic fellowships or scholarly activities involving notable figures

    oai_token-act-pair · gpt-3.5-turbo

    references to notable filmmakers and fellowship programs related to cinema

    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
    store
    -0.74
     unden
    -0.67
     overloaded
    -0.67
    quel
    -0.67
    ãĥĺ
    -0.64
    isine
    -0.63
     barric
    -0.62
     rall
    -0.62
    que
    -0.62
    itans
    -0.61
    POSITIVE LOGITS
     Fell
    1.11
     fellows
    0.97
     fellowship
    0.97
     Fellowship
    0.91
    inguished
    0.87
    ees
    0.87
    owship
    0.87
    hips
    0.81
     Fellow
    0.80
     Graduate
    0.77
    Activations Density 0.017%

    No Known Activations