© 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. 16880
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "noble" and its variations, indicating a focus on nobility or noble characters

    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
    NING
    -0.72
    eers
    -0.71
     Animation
    -0.71
    ization
    -0.69
    icago
    -0.68
    eering
    -0.68
    DERR
    -0.67
    ãĥ´ãĤ¡
    -0.67
     Ya
    -0.66
     Wonderland
    -0.65
    POSITIVE LOGITS
    vic
    0.74
    bridge
    0.74
    ktop
    0.74
    rie
    0.73
    moral
    0.72
    witz
    0.71
    ira
    0.70
    idate
    0.70
    boats
    0.69
    ocrats
    0.69
    Activations Density 0.093%

    No Known Activations