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. 7-RES-JB
    6. 1167
    Prev
    Next
    INDEX
    Explanations

    references to the term "bachelor" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Bachelor" and "ski" along with variations of "Rachel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.80
    iets
    -0.78
     Bourbon
    -0.76
    nesses
    -0.76
    anos
    -0.73
     Fired
    -0.72
     Liang
    -0.72
    arian
    -0.70
    ano
    -0.70
    nikov
    -0.70
    POSITIVE LOGITS
    uthor
    0.87
     mathemat
    0.80
    ntil
    0.79
    ounty
    0.79
    ĺħ
    0.77
    merce
    0.77
    £
    0.76
    «
    0.76
    atorial
    0.75
    uum
    0.72
    Activations Density 0.063%

    No Known Activations