© 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. 7-RES-JB
    11. 1805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instant" followed by a numeric value denoting strength of activation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to immediacy or quick access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.89
    pherd
    -0.78
    byss
    -0.78
    ALD
    -0.77
    bard
    -0.76
    unal
    -0.75
    atche
    -0.72
    llah
    -0.72
    ramids
    -0.71
    ^^^^
    -0.70
    POSITIVE LOGITS
    aneously
    1.96
    aneous
    1.48
     gratification
    1.46
    iation
    1.23
    iations
    1.20
     replay
    1.19
    iated
    1.14
    iating
    1.12
    iate
    0.99
    iates
    0.97
    Activations Density 0.017%

    No Known Activations