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. 12-RES-JB
    6. 6932
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal experiences related to health or social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to legal and bureaucratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     synthes
    -0.68
     electr
    -0.67
     revital
    -0.66
     synerg
    -0.66
     wielded
    -0.65
     sculpt
    -0.65
    eco
    -0.64
     pioneering
    -0.63
     blending
    -0.63
    ankind
    -0.63
    POSITIVE LOGITS
    FY
    0.97
     Emails
    0.96
    Apparently
    0.91
     USPS
    0.89
     DMV
    0.88
     emailed
    0.87
     apologized
    0.86
     refund
    0.84
    Customer
    0.84
     THEY
    0.83
    Activations Density 0.768%

    No Known Activations