© 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. 1-RES-JB
    11. 23592
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'situation' or 'evacuation'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "situation" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.70
    blue
    -0.64
    thouse
    -0.64
    die
    -0.61
     sunglasses
    -0.60
    Sea
    -0.60
     cre
    -0.59
    stru
    -0.58
     hearty
    -0.57
     continental
    -0.57
    POSITIVE LOGITS
    uations
    1.84
    uates
    1.81
    uated
    1.78
    uation
    1.78
    uating
    1.72
    uate
    1.57
    ually
    0.84
    iev
    0.83
    terday
    0.83
    aution
    0.83
    Activations Density 0.010%

    No Known Activations