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. 19546
    Prev
    Next
    INDEX
    Explanations

    information about notable individuals – their professions, nationalities, and birth dates

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and their professions or contributions

    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
     }}
    -0.77
    acca
    -0.72
    oother
    -0.72
    ĪĴ
    -0.71
    luaj
    -0.70
    ]}
    -0.70
    PHOTOS
    -0.68
    â̦)
    -0.68
    Newsletter
    -0.68
    uers
    -0.68
    POSITIVE LOGITS
     approximately
    0.70
     located
    0.70
     northwest
    0.69
     Published
    0.68
     Alternate
    0.68
     Approximately
    0.68
    Overview
    0.67
    Contents
    0.67
     Founding
    0.66
     Miscellaneous
    0.65
    Activations Density 0.605%

    No Known Activations