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. 8-RES-JB
    6. 8703
    Prev
    Next
    INDEX
    Explanations

    text related to editing or formatting of content, such as headings, lists, or awards

    oai_token-act-pair · gpt-3.5-turbo

    references to awards and nominations in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    milo
    -0.75
     eleph
    -0.63
     reconc
    -0.61
     noses
    -0.59
     discour
    -0.59
    abba
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.57
    è£
    -0.57
     adolesc
    -0.56
     susp
    -0.55
    POSITIVE LOGITS
     ]
    0.96
     ])
    0.88
     ],
    0.82
     ][
    0.82
    Spoiler
    0.79
     Edit
    0.76
      
    0.73
    "]=>
    0.73
     âĨij
    0.71
     ÃĹ
    0.70
    Activations Density 0.033%

    No Known Activations