© 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. 22510
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Nash" at varying activations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or entity denoted by variations of the token "ash"

    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
     pregn
    -0.68
    etheless
    -0.67
    STER
    -0.60
    worldly
    -0.60
    sworth
    -0.58
    ster
    -0.58
    oplan
    -0.57
     elig
    -0.56
    eering
    -0.56
     cavity
    -0.56
    POSITIVE LOGITS
    nikov
    1.03
    IELD
    0.97
    ield
    0.91
    anu
    0.89
    imi
    0.87
    adow
    0.84
    rine
    0.84
    IFT
    0.84
    ti
    0.82
    ares
    0.82
    Activations Density 0.036%

    No Known Activations