© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16682
    Prev
    Next
    INDEX
    Explanations

    network-related strings like IP addresses and ports

    oai_token-act-pair · gpt-3.5-turbo

    colons and annotated data structures potentially indicating configuration settings or code

    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
     Jude
    -0.65
     behavi
    -0.64
     sided
    -0.63
     troubles
    -0.62
     Gulf
    -0.61
     back
    -0.60
     outright
    -0.60
     Sant
    -0.59
     Pratt
    -0.58
     whip
    -0.58
    POSITIVE LOGITS
    hover
    1.19
    memory
    0.99
    YES
    0.97
    latest
    0.96
    before
    0.89
    checked
    0.84
    eyes
    0.84
    344
    0.84
    3000
    0.83
    5000
    0.83
    Activations Density 0.088%

    No Known Activations