© 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. 1-RES-JB
    11. 22315
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to institutional titles or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to international or diplomatic relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schne
    -0.75
    代
    -0.74
     Lomb
    -0.74
    UC
    -0.71
    \\\\\\\\\\\\\\\\
    -0.71
    ä¸Ń
    -0.69
     Sicily
    -0.69
    JC
    -0.66
    ãĢIJ
    -0.66
    ãĢĮ
    -0.65
    POSITIVE LOGITS
    hips
    1.55
     Relations
    1.26
    hip
    0.93
    nect
    0.92
    pring
    0.90
    hops
    0.89
     relations
    0.85
     Entity
    0.85
    terness
    0.82
    rations
    0.81
    Activations Density 0.008%

    No Known Activations