© 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. 3-RES-JB
    11. 20069
    Prev
    Next
    INDEX
    Explanations

    words related to immediacy or speed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "instant" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.84
    atche
    -0.80
    yss
    -0.74
    acus
    -0.69
     Bureau
    -0.67
    pherd
    -0.67
    ALD
    -0.66
    bard
    -0.63
    ramids
    -0.63
     Tate
    -0.63
    POSITIVE LOGITS
    aneously
    1.97
     gratification
    1.39
    aneous
    1.28
    iations
    1.24
    iated
    1.18
    iation
    1.16
    iating
    1.10
     replay
    1.04
     instant
    1.02
    iates
    0.98
    Activations Density 0.007%

    No Known Activations