© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13614
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    specific user mentions and interactive elements in online content

    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
     Perez
    -0.82
     Gins
    -0.82
     GP
    -0.81
     Franco
    -0.80
     Hasan
    -0.80
     Cole
    -0.79
     Gian
    -0.78
     Lei
    -0.77
     Fein
    -0.76
     Ryan
    -0.76
    POSITIVE LOGITS
    arn
    0.94
    ¥µ
    0.91
    AV
    0.89
    ya
    0.86
    Ĵ
    0.85
    chanted
    0.83
    av
    0.83
     AV
    0.83
    BOX
    0.82
     Vessel
    0.81
    Activations Density 0.366%

    No Known Activations