Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20107
    Prev
    Next
    INDEX
    Explanations

    words related to policies, legislation, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to community contributions and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illions
    -0.66
    ãĥ´ãĤ¡
    -0.60
    xxxx
    -0.59
    bare
    -0.58
    sorry
    -0.58
    ãĤ¦ãĤ¹
    -0.56
    fuck
    -0.56
     horrend
    -0.56
    shit
    -0.55
    death
    -0.55
    POSITIVE LOGITS
     additional
    0.70
     further
    0.68
     similarly
    0.66
     similar
    0.65
     also
    0.63
     later
    0.62
     additionally
    0.60
     complementary
    0.59
     expanded
    0.58
     likewise
    0.57
    Activations Density 1.471%

    No Known Activations