© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23290
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Susie"

    oai_token-act-pair · gpt-3.5-turbo

    names associated with a specific individual or character

    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
     learning
    -0.78
    ingo
    -0.77
     overhead
    -0.76
     living
    -0.74
    anwhile
    -0.73
     forging
    -0.68
     effic
    -0.68
     sorting
    -0.68
     crafting
    -0.68
    rogens
    -0.67
    POSITIVE LOGITS
    Sus
    1.42
     Sus
    1.14
    annah
    0.99
    pic
    0.95
    pect
    0.94
    pecting
    0.93
    itiz
    0.89
    pected
    0.88
    pects
    0.88
    ethe
    0.81
    Activations Density 0.007%

    No Known Activations