© 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. 8-RES-JB
    11. 23561
    Prev
    Next
    INDEX
    Explanations

    instances where there are requests to try again later

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "try" in various contexts

    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
    icipated
    -0.70
    obyl
    -0.70
    HEAD
    -0.61
    dylib
    -0.59
    iations
    -0.59
    atform
    -0.57
    inational
    -0.57
    actionDate
    -0.57
    head
    -0.57
    pread
    -0.57
    POSITIVE LOGITS
    nir
    0.85
     harder
    0.84
     unsuccessfully
    0.83
    ":"/
    0.71
     contacting
    0.67
     Mayo
    0.66
     Nex
    0.65
     again
    0.65
    ãĤ§
    0.61
    geon
    0.61
    Activations Density 0.017%

    No Known Activations