© 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. 9-RES-JB
    11. 11285
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving information via email or staying updated with news

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in your inbox"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -0.81
    etheless
    -0.77
     distances
    -0.68
    netflix
    -0.67
    oras
    -0.66
    emis
    -0.65
    edIn
    -0.64
     convol
    -0.63
     drift
    -0.63
     occasions
    -0.62
    POSITIVE LOGITS
     advance
    0.90
     lieu
    0.81
     situ
    0.79
    clusions
    0.78
     conjunction
    0.78
     chronological
    0.76
     order
    0.75
     accordance
    0.73
    alien
    0.71
     Translation
    0.71
    Activations Density 0.094%

    No Known Activations