© 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. 8-RES-JB
    11. 3848
    Prev
    Next
    INDEX
    Explanations

    phrases related to visitors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of visitors in various contexts

    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
    lain
    -0.91
    negie
    -0.73
    rum
    -0.66
    ukes
    -0.64
    esson
    -0.61
    lished
    -0.58
    otomy
    -0.58
    ©¶æ
    -0.58
    stood
    -0.57
    SourceFile
    -0.57
    POSITIVE LOGITS
     attractions
    0.92
    hip
    0.91
    erv
    0.78
     attraction
    0.77
    cript
    0.77
     visiting
    0.73
     beware
    0.73
    issance
    0.72
    elcome
    0.70
     visitors
    0.70
    Activations Density 0.040%

    No Known Activations