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. 11-RES-JB
    6. 7275
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location or holiday event

    oai_token-act-pair · gpt-3.5-turbo

    references to "New" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.73
     advised
    -0.69
    ional
    -0.67
     absence
    -0.67
    uca
    -0.66
    ouses
    -0.66
     dod
    -0.66
     currently
    -0.63
     absent
    -0.63
     sqor
    -0.62
    POSITIVE LOGITS
     York
    1.49
     Zealand
    1.46
     Yorkers
    1.44
     Yorker
    1.43
     Orleans
    1.38
     Hampshire
    1.21
     Year
    1.21
     Testament
    1.17
    York
    1.17
     Jersey
    1.16
    Activations Density 0.047%

    No Known Activations