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. 9-RES-JB
    6. 164
    Prev
    Next
    INDEX
    Explanations

    references to writing materials like diaries and journals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diaries and journaling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oval
    -0.70
    bite
    -0.70
    dh
    -0.69
    etooth
    -0.68
    OV
    -0.66
    pta
    -0.64
    tackle
    -0.64
    blocking
    -0.64
    baugh
    -0.64
    EStreamFrame
    -0.63
    POSITIVE LOGITS
     entries
    1.06
     Entry
    0.98
     Pages
    0.85
     reader
    0.80
     notebook
    0.80
     entry
    0.80
     Journals
    0.79
     journals
    0.78
     journal
    0.77
     archives
    0.77
    Activations Density 0.133%

    No Known Activations