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. 9-RES-JB
    6. 1156
    Prev
    Next
    INDEX
    Explanations

    mentions of formal organizations or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.78
     Rockies
    -0.73
    Timer
    -0.71
    ullivan
    -0.69
     subp
    -0.68
    THER
    -0.67
    nir
    -0.66
     sled
    -0.65
    stroke
    -0.65
    storms
    -0.65
    POSITIVE LOGITS
    arians
    1.03
    itutional
    1.01
    ally
    0.93
    utions
    0.90
     institutions
    0.86
     affili
    0.85
     institution
    0.81
    arian
    0.80
    ament
    0.80
    ifice
    0.78
    Activations Density 0.027%

    No Known Activations