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. 0-RES-JB
    6. 20924
    Prev
    Next
    INDEX
    Explanations

    proper nouns relating to financial institutions or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly related to economic policies or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veget
    -0.76
     fibre
    -0.74
     plaque
    -0.71
    SOURCE
    -0.69
    Neal
    -0.68
     ashes
    -0.68
    Indian
    -0.66
     stew
    -0.66
     slate
    -0.66
     rubbish
    -0.66
    POSITIVE LOGITS
     Drag
    3.53
    Drag
    2.46
     DRAG
    1.50
     Drac
    1.32
     Bundes
    1.29
     Mug
    1.09
    dra
    1.02
     Berk
    1.01
     Barbar
    1.01
     Sorceress
    1.00
    Activations Density 0.055%

    No Known Activations