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. 0-RES-JB
    6. 5857
    Prev
    Next
    INDEX
    Explanations

    references to the entrepreneur and SpaceX CEO Elon Musk

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Elon Musk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ce
    -0.67
    CI
    -0.63
    akura
    -0.63
     cross
    -0.62
    JP
    -0.61
     counter
    -0.61
    VS
    -0.60
    ante
    -0.59
     arch
    -0.58
    xx
    -0.58
    POSITIVE LOGITS
     Musk
    4.23
     Elon
    1.97
    Mus
    1.83
     SpaceX
    1.82
     Tesla
    1.66
    Tesla
    1.60
     Bezos
    1.55
     Thiel
    1.20
     Hawking
    1.14
     Tillerson
    1.07
    Activations Density 0.017%

    No Known Activations