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. 19447
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "named" followed by a person's name

    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
    EMS
    -0.78
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.72
    union
    -0.70
    hibition
    -0.70
    Constructed
    -0.68
    qua
    -0.67
    irth
    -0.67
    âķIJâķIJ
    -0.67
     practiced
    -0.66
    Interstitial
    -0.66
    POSITIVE LOGITS
     TOM
    0.89
     Xen
    0.79
     Artemis
    0.77
     Hann
    0.75
     Karl
    0.73
     Ares
    0.73
     surn
    0.73
     Shad
    0.73
     Nemesis
    0.72
     Spot
    0.71
    Activations Density 0.027%

    No Known Activations