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. 617
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to familial and social structures

    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
     theirs
    -0.68
     colleagues
    -0.64
     compat
    -0.61
     tha
    -0.60
     commits
    -0.60
     another
    -0.60
     lia
    -0.58
     Germany
    -0.57
     yesterday
    -0.57
     accompl
    -0.56
    POSITIVE LOGITS
     afterlife
    1.11
    urgy
    1.11
    atre
    1.07
    ocracy
    1.03
     sexes
    0.97
    ocratic
    0.97
    oret
    0.95
     Quran
    0.88
    ater
    0.88
     arts
    0.88
    Activations Density 0.607%

    No Known Activations