© 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. 8-RES-JB
    11. 24499
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to sudden or unexpected events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sudden" and related concepts of unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.82
    models
    -0.81
    adr
    -0.72
    gdala
    -0.72
    emark
    -0.71
    ribe
    -0.71
    tops
    -0.70
    requires
    -0.70
    rica
    -0.70
    =-=-=-=-
    -0.69
    POSITIVE LOGITS
     departure
    1.22
     onset
    1.17
    aneously
    1.13
     death
    1.12
     arrival
    1.11
    aneous
    1.09
     gratification
    1.06
     cessation
    1.06
     demise
    1.05
     succession
    1.05
    Activations Density 0.077%

    No Known Activations