© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1118
    Prev
    Next
    INDEX
    Explanations

    terms related to digital communication and data management, particularly references to Skype contacts and user information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to user accounts and contact management in digital platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wart
    -0.76
    krit
    -0.72
    judicial
    -0.71
    cipled
    -0.71
    utic
    -0.69
     Akin
    -0.68
     Moral
    -0.66
    quickShipAvailable
    -0.66
    glas
    -0.65
     Flan
    -0.64
    POSITIVE LOGITS
     dataset
    0.96
    Details
    0.93
     metadata
    0.92
     IDs
    0.88
     directory
    0.87
     info
    0.86
    Data
    0.85
    Info
    0.85
     directories
    0.83
     data
    0.83
    Activations Density 0.520%

    No Known Activations