© 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. 17327
    Prev
    Next
    INDEX
    Explanations

    the term "stint" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to temporary engagements or periods of time spent in specific occupations or situations

    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
    hammad
    -0.88
    ported
    -0.67
    ramid
    -0.63
     Federation
    -0.62
    hedral
    -0.61
    trust
    -0.60
    actionDate
    -0.60
    facts
    -0.59
     Commissioners
    -0.58
    evidence
    -0.58
    POSITIVE LOGITS
     stint
    1.14
    ilitation
    0.84
     abroad
    0.77
    ayson
    0.75
     assignments
    0.75
     overseas
    0.74
    ional
    0.74
    ãĤ¡
    0.74
    ionage
    0.73
    ãĤ½
    0.73
    Activations Density 0.013%

    No Known Activations