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. 1643
    Prev
    Next
    INDEX
    Explanations

    words related to editing or making changes in a document or text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "edit" in various contexts

    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
     eleph
    -0.84
    mercial
    -0.71
    ñ
    -0.69
    aditional
    -0.66
     mosqu
    -0.66
    senal
    -0.64
    milo
    -0.64
     adolesc
    -0.64
     exting
    -0.62
     reconc
    -0.61
    POSITIVE LOGITS
     ]
    1.58
     ],
    1.18
     ])
    1.16
     ][
    1.15
     ].
    1.05
     ];
    0.89
    ]
    0.88
     Edit
    0.87
     edit
    0.86
     )]
    0.86
    Activations Density 0.009%

    No Known Activations