Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16468
    Prev
    Next
    INDEX
    Explanations

    alternative names or aliases for people or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote alternative names or aliases for individuals or entities

    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
    ittal
    -0.82
    atem
    -0.71
    osc
    -0.70
    arching
    -0.69
    avorable
    -0.68
    ÃŃs
    -0.67
    chini
    -0.67
    iegel
    -0.65
    offer
    -0.65
    udence
    -0.65
    POSITIVE LOGITS
     Despair
    0.80
     HERO
    0.79
     Skydragon
    0.78
     Known
    0.76
    MJ
    0.75
     CoC
    0.75
     Crazy
    0.74
     Haram
    0.73
     "#
    0.72
     Splash
    0.71
    Activations Density 0.051%

    No Known Activations