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. 10-RES-JB
    6. 8859
    Prev
    Next
    INDEX
    Explanations

    dates or events within text

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.88
     favour
    -0.85
     disciplines
    -0.84
     edged
    -0.83
     governed
    -0.82
     accelerator
    -0.79
     regener
    -0.79
     persu
    -0.79
     commissions
    -0.77
     greenhouse
    -0.77
    POSITIVE LOGITS
    Looks
    1.66
    RIP
    1.65
    @
    1.64
    Others
    1.56
    Wow
    1.56
    Cong
    1.55
    https
    1.55
    Advertisements
    1.54
    BRE
    1.50
    Apparently
    1.49
    Activations Density 0.201%

    No Known Activations