© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6937
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly last names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the last name Reynolds

    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
    nesses
    -0.98
    itarian
    -0.90
    ness
    -0.89
    hip
    -0.82
    ian
    -0.76
    ingly
    -0.76
    inations
    -0.75
    ¢
    -0.74
    ians
    -0.73
    ansas
    -0.72
    POSITIVE LOGITS
    OPLE
    0.86
     McF
    0.78
    ISTER
    0.75
    isters
    0.71
    CLASSIFIED
    0.70
     tremend
    0.67
     cavity
    0.64
     conclud
    0.63
    issions
    0.61
    adden
    0.61
    Activations Density 0.133%

    No Known Activations