© 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. 11-RES-JB
    11. 7530
    Prev
    Next
    INDEX
    Explanations

    instances where the term "contact" is being used

    oai_token-act-pair · gpt-3.5-turbo

    references to contact information or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    corn
    -0.71
    cott
    -0.70
    quest
    -0.64
    icz
    -0.63
     Sabha
    -0.62
     compr
    -0.61
    perm
    -0.59
    gallery
    -0.59
    SpaceEngineers
    -0.58
    sung
    -0.58
    POSITIVE LOGITS
     lenses
    1.06
     tracing
    0.92
    kson
    0.92
    ioned
    0.92
     lens
    0.83
    ivity
    0.80
    ees
    0.78
    less
    0.75
    imei
    0.74
    ually
    0.74
    Activations Density 0.073%

    No Known Activations