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. 22689
    Prev
    Next
    INDEX
    Explanations

    different types or attributes of objects

    oai_token-act-pair · gpt-3.5-turbo

    elements related to quantities and classifications

    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
    etheless
    -0.71
    çͰ
    -0.60
    ãĤ©
    -0.59
    CONCLUS
    -0.58
    .).
    -0.57
     Conclusion
    -0.55
    umblr
    -0.55
    "!
    -0.54
    ))))
    -0.54
     WRITE
    -0.54
    POSITIVE LOGITS
     or
    1.14
     and
    1.02
    ,
    0.78
     but
    0.71
    ,[
    0.70
     while
    0.67
     because
    0.63
     ("
    0.62
    ®,
    0.61
     âĢķ
    0.60
    Activations Density 1.163%

    No Known Activations