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. 22935
    Prev
    Next
    INDEX
    Explanations

    phrases related to innovative ideas, research, and technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the word "by" followed by various actions or clauses

    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
    ãĤ´ãĥ³
    -0.80
    ãĥ£
    -0.74
    rossover
    -0.73
    cffffcc
    -0.72
    visory
    -0.72
    displayText
    -0.70
    bernatorial
    -0.67
    ãģł
    -0.66
    intosh
    -0.66
    ioxide
    -0.64
    POSITIVE LOGITS
     we
    1.12
     you
    0.92
     they
    0.88
     however
    0.81
     researchers
    0.76
     coupled
    0.76
     moreover
    0.76
     readers
    0.75
     viewers
    0.75
     learners
    0.74
    Activations Density 0.144%

    No Known Activations