© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 16174
    Prev
    Next
    INDEX
    Explanations

    words related to physical contact and communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contact"

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

    No Comments

    Negative Logits
    corn
    -0.90
    reci
    -0.83
    ARR
    -0.81
    ZI
    -0.67
     concession
    -0.66
    serving
    -0.66
    acht
    -0.66
    ĻĤ
    -0.66
    cott
    -0.65
    YR
    -0.64
    POSITIVE LOGITS
     contact
    1.02
     lenses
    0.91
     contacts
    0.91
    ysis
    0.87
    ioned
    0.83
    imei
    0.82
    iquette
    0.79
     tracing
    0.77
    kson
    0.76
     Contact
    0.75
    Activations Density 0.017%

    No Known Activations