© 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. 11-RES-JB
    11. 18692
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to suppliers and providers in the context of technology and business

    oai_token-act-pair · gpt-3.5-turbo

    terms related to suppliers and vendors in a market context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    equality
    -0.71
    croft
    -0.68
    aughs
    -0.66
    ceed
    -0.65
    usalem
    -0.65
    izoph
    -0.64
    reditary
    -0.62
    sle
    -0.62
    olit
    -0.61
    owan
    -0.61
    POSITIVE LOGITS
    hips
    0.93
     beware
    0.82
     supplying
    0.81
     specializing
    0.79
     headquartered
    0.78
     offering
    0.75
     warranties
    0.74
    piracy
    0.73
    hip
    0.70
     WHO
    0.70
    Activations Density 0.196%

    No Known Activations