© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific details or components that stand out in a description

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" and its repeated use in different contexts

    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
     Corps
    -0.61
    WARE
    -0.58
    Desk
    -0.57
    "],"
    -0.57
    natureconservancy
    -0.56
     Breat
    -0.56
     Salam
    -0.55
     Pass
    -0.55
    ãĤĬ
    -0.54
     Recover
    -0.54
    POSITIVE LOGITS
     mattered
    0.81
     resulted
    0.79
    iago
    0.78
     culminated
    0.77
     fateful
    0.76
    eatures
    0.76
     arose
    0.76
     pesky
    0.76
    ÃĥÃĤ
    0.74
    allery
    0.74
    Activations Density 0.485%

    No Known Activations