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. 3-RES-JB
    6. 2727
    Prev
    Next
    INDEX
    Explanations

    words related to depicting or representing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "portray" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wegian
    -0.78
    sterdam
    -0.78
    duct
    -0.77
    foreseen
    -0.76
    raid
    -0.72
    foundation
    -0.68
    ffic
    -0.67
    speak
    -0.66
    pled
    -0.65
    scrib
    -0.64
    POSITIVE LOGITS
     portray
    1.17
     portrays
    1.14
     portrayal
    1.03
    rities
    1.00
     depictions
    0.99
     portraying
    0.95
     portrayed
    0.91
    DonaldTrump
    0.86
     portraits
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.81
    Activations Density 0.017%

    No Known Activations