© 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. 7-RES-JB
    11. 13961
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and business activities

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters or characters forming specific types of important content identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anu
    -1.09
    ¹
    -0.88
    ¸
    -0.86
    aris
    -0.84
    umat
    -0.84
    ÄŁ
    -0.84
    ·
    -0.83
    oto
    -0.83
    IJ
    -0.81
    anta
    -0.81
    POSITIVE LOGITS
     seating
    0.71
     replacements
    0.70
     heights
    0.69
     tones
    0.68
    hood
    0.68
     representations
    0.67
     penetration
    0.67
     redundancy
    0.67
    ingly
    0.66
     rooting
    0.66
    Activations Density 0.270%

    No Known Activations