© 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. 16933
    Prev
    Next
    INDEX
    Explanations

    references to visitors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of visitors or tourists

    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
    lain
    -0.90
    SourceFile
    -0.82
    esson
    -0.72
    ukes
    -0.69
    aucuses
    -0.64
    rum
    -0.63
    negie
    -0.63
    ©¶æ
    -0.61
    onen
    -0.60
    rov
    -0.59
    POSITIVE LOGITS
    hip
    0.96
     attractions
    0.95
     visiting
    0.90
     attraction
    0.86
    seeing
    0.84
    hips
    0.83
     flock
    0.78
     alike
    0.78
    cript
    0.77
     viewing
    0.75
    Activations Density 0.044%

    No Known Activations