© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 215
    Prev
    Next
    INDEX
    Explanations

    phrases related to a change or reversal of some kind

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate changes or reversals in context

    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
    Catalog
    -0.75
     partName
    -0.66
    çīĪ
    -0.65
    BG
    -0.64
    crit
    -0.63
    ertodd
    -0.61
    yers
    -0.61
    UID
    -0.61
    Rs
    -0.60
     kitchens
    -0.59
    POSITIVE LOGITS
     sorts
    0.88
     course
    0.80
     electrons
    0.72
     hostilities
    0.67
    hire
    0.63
    emale
    0.62
    skill
    0.62
    Course
    0.62
     arms
    0.62
     Goods
    0.60
    Activations Density 0.269%

    No Known Activations