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. 4-RES-JB
    6. 8297
    Prev
    Next
    INDEX
    Explanations

    references to the entrepreneur and CEO Elon Musk

    oai_token-act-pair · gpt-3.5-turbo

    references to Elon Musk

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

    No Comments

    Negative Logits
    ~~~~~~~~~~~~~~~~
    -0.82
    cgi
    -0.67
    Irish
    -0.64
     Gael
    -0.64
     Forbidden
    -0.64
    ADVERTISEMENT
    -0.64
     Examiner
    -0.63
    scenes
    -0.62
    spring
    -0.61
    EY
    -0.61
    POSITIVE LOGITS
     Musk
    1.52
     Elon
    1.05
    ius
    0.85
    uates
    0.82
    ometer
    0.81
    istor
    0.78
    pad
    0.76
    essen
    0.75
    issan
    0.71
    osure
    0.71
    Activations Density 0.005%

    No Known Activations