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. 10-RES-JB
    6. 15749
    Prev
    Next
    INDEX
    Explanations

    specific words related to proper nouns like names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     potentially
    -0.64
     ÂŃ
    -0.64
     however
    -0.64
     pleas
    -0.63
     legitimately
    -0.63
     correctly
    -0.61
     prompt
    -0.60
     given
    -0.60
     infuri
    -0.60
     appealing
    -0.60
    POSITIVE LOGITS
    ocene
    0.77
    idia
    0.75
    tek
    0.72
    negie
    0.71
    usalem
    0.71
    apolis
    0.69
    iami
    0.67
    acus
    0.67
    ĸļ
    0.65
    onia
    0.65
    Activations Density 0.716%

    No Known Activations