© 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. 10-RES-JB
    11. 9226
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and political figures

    oai_token-act-pair · gpt-3.5-turbo

    words related to the suffix 'ine', which often denote chemical compounds or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.83
    dyl
    -0.80
    ypes
    -0.80
    ODUCT
    -0.78
    rity
    -0.73
    rieved
    -0.71
    abies
    -0.71
    opher
    -0.69
    hips
    -0.67
    ivated
    -0.67
    POSITIVE LOGITS
    phrine
    1.53
    lla
    1.28
    jad
    1.28
    lli
    1.13
    hart
    1.11
    llo
    1.11
    apple
    1.04
    backer
    0.96
    cone
    0.89
    ering
    0.85
    Activations Density 0.088%

    No Known Activations