© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    highly attractive attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "attractive" in various contexts

    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
    cedented
    -0.87
    cham
    -0.87
    othe
    -0.83
    ignt
    -0.79
    bel
    -0.77
    othing
    -0.76
    iche
    -0.76
    feeding
    -0.75
     Airl
    -0.75
    apolis
    -0.71
    POSITIVE LOGITS
     lure
    0.96
     proposition
    0.92
     attractive
    0.88
     prospects
    0.85
     prospect
    0.84
     targets
    0.79
     tempt
    0.77
     attractiveness
    0.76
     attraction
    0.73
     attract
    0.73
    Activations Density 0.062%

    No Known Activations