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. 0-RES-JB
    6. 19463
    Prev
    Next
    INDEX
    Explanations

    words related to the profession or equipment of a disc jockey (DJ)

    oai_token-act-pair · gpt-3.5-turbo

    references to DJs and their activities

    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
    ions
    -0.67
    etimes
    -0.65
    struction
    -0.64
     wounds
    -0.64
     Sap
    -0.63
    bowl
    -0.62
     shells
    -0.61
     centers
    -0.60
    Amount
    -0.60
     soluble
    -0.60
    POSITIVE LOGITS
     DJ
    3.92
    DJ
    3.18
     DJs
    2.82
     dj
    1.73
    dj
    1.56
     Dj
    1.44
     rapper
    1.39
     BJ
    1.32
     Disco
    1.28
     dancer
    1.28
    Activations Density 0.025%

    No Known Activations