© 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. 16165
    Prev
    Next
    INDEX
    Explanations

    various references to 'instant' actions or items

    oai_token-act-pair · gpt-3.5-turbo

    references to immediacy or speed in actions or effects

    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
    xual
    -0.85
    yss
    -0.76
    atche
    -0.74
    ALD
    -0.71
    anners
    -0.71
    ramids
    -0.70
    jri
    -0.70
    pherd
    -0.69
    haps
    -0.69
    ongyang
    -0.68
    POSITIVE LOGITS
    aneously
    1.97
    aneous
    1.42
     gratification
    1.39
    iations
    1.29
    iation
    1.22
    iated
    1.20
    iating
    1.16
     replay
    1.13
    iates
    1.01
    iate
    1.00
    Activations Density 0.010%

    No Known Activations