© 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. 1-RES-JB
    11. 7661
    Prev
    Next
    INDEX
    Explanations

    mentions of user experience (UX) and usability in texts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to user experience (UX) and usability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hood
    -0.86
    SPONSORED
    -0.85
    shaw
    -0.76
    alcohol
    -0.75
    stall
    -0.74
    bell
    -0.73
    stellar
    -0.69
    stals
    -0.69
    Animal
    -0.66
    mother
    -0.65
    POSITIVE LOGITS
     usability
    0.91
    umerable
    0.85
     UX
    0.83
    selage
    0.81
    ictionary
    0.79
    iquette
    0.77
    ulner
    0.75
    upid
    0.75
    -+-+
    0.75
    okin
    0.75
    Activations Density 0.020%

    No Known Activations