© 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. 7495
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of hurdles or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    words related to challenges or obstacles, often metaphorically referred to as "hoops."

    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
    gments
    -0.79
    ication
    -0.72
    iability
    -0.71
    ensing
    -0.71
    izen
    -0.69
     robber
    -0.68
     Ide
    -0.67
    ulla
    -0.66
     pardon
    -0.65
    erton
    -0.63
    POSITIVE LOGITS
     hoops
    1.20
     hoop
    1.03
    complex
    0.78
    Thumbnail
    0.77
    awk
    0.77
    Wa
    0.77
    consuming
    0.76
    rw
    0.74
     Hole
    0.73
    wiki
    0.73
    Activations Density 0.021%

    No Known Activations