© 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. 3143
    Prev
    Next
    INDEX
    Explanations

    information related to copyrights, publications, and permissions

    oai_token-act-pair · gpt-3.5-turbo

    copyright and attribution information

    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
     haunt
    -0.87
    adian
    -0.75
    igraph
    -0.65
    nikov
    -0.61
     queue
    -0.60
    behind
    -0.59
    taker
    -0.59
     haun
    -0.57
    shown
    -0.57
    TON
    -0.57
    POSITIVE LOGITS
    Lic
    0.77
     All
    0.73
    ortium
    0.70
     Contribut
    0.67
     Reprodu
    0.67
     Partnership
    0.65
    verning
    0.64
    Contribut
    0.64
     contributors
    0.62
     trademark
    0.62
    Activations Density 0.035%

    No Known Activations