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. 11-RES-JB
    6. 3966
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting the importance or key aspect of a concept

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing significance and foundational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Cosponsors
    -1.03
     largeDownload
    -0.82
    zens
    -0.82
    eor
    -0.79
    ittees
    -0.77
    ilst
    -0.75
    arnaev
    -0.74
    arger
    -0.74
    Enlarge
    -0.72
    Others
    -0.71
    POSITIVE LOGITS
     contagious
    1.20
     bliss
    1.13
     rewarded
    1.09
     paramount
    1.00
     futile
    0.99
     virtue
    0.97
     preferable
    0.97
     synonymous
    0.96
     Virtue
    0.94
     prized
    0.94
    Activations Density 0.159%

    No Known Activations