© 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. 11-RES-JB
    11. 162
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and numerical values, such as amounts, sizes, and other data

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    few
    -0.91
    months
    -0.84
    States
    -0.83
    heses
    -0.83
     Cosponsors
    -0.78
    groups
    -0.77
    heid
    -0.75
    parts
    -0.75
    entimes
    -0.75
    999
    -0.75
    POSITIVE LOGITS
     usable
    1.00
     unprotected
    0.83
     coastline
    0.81
     pure
    0.80
     extra
    0.79
     ground
    0.78
     additional
    0.78
     fresh
    0.77
     concentrated
    0.76
     uninterrupted
    0.75
    Activations Density 0.090%

    No Known Activations