© 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. 10-RES-JB
    11. 13905
    Prev
    Next
    INDEX
    Explanations

    information related to event details, locations, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -0.78
    ORPG
    -0.77
    âĹ¼
    -0.77
     Seym
    -0.77
    TEXTURE
    -0.73
    ÙĴ
    -0.70
    ertodd
    -0.70
    vironments
    -0.69
    ̶
    -0.67
    Community
    -0.67
    POSITIVE LOGITS
     unspecified
    0.93
     TBA
    0.92
     unknown
    0.92
     expires
    0.91
     TBD
    0.89
     req
    0.87
     instr
    0.83
     avail
    0.83
     varies
    0.83
     typo
    0.81
    Activations Density 0.361%

    No Known Activations