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. 6058
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities, such as "Tyler Ulbricht" and "Americas"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ul" and mentions of the "Americas."

    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
    psons
    -0.86
    plugin
    -0.82
     Bloom
    -0.78
    etchup
    -0.78
    ðĿ
    -0.77
    =#
    -0.74
     welf
    -0.74
    overty
    -0.74
     sitcom
    -0.73
    pmwiki
    -0.73
    POSITIVE LOGITS
     Ul
    2.02
    Ul
    1.65
     Americas
    1.51
     unse
    1.46
     Roh
    1.44
     commemor
    1.24
     Nad
    1.19
     Bah
    1.02
     Ultr
    0.98
     altern
    0.96
    Activations Density 0.061%

    No Known Activations