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. 0-RES-JB
    6. 4521
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data management such as "Retrieval" or "Retention"

    oai_token-act-pair · gpt-3.5-turbo

    references to retirement and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SO
    -0.70
     chalk
    -0.70
    onomy
    -0.68
    Connell
    -0.66
     sonic
    -0.65
     horn
    -0.65
    innie
    -0.65
    onal
    -0.64
    Ãį
    -0.62
     alley
    -0.62
    POSITIVE LOGITS
     Ret
    3.83
    Ret
    2.86
    ret
    1.95
     ret
    1.79
     retri
    1.71
     RET
    1.67
     retina
    1.33
     Retro
    1.27
     retrie
    1.23
     Retirement
    1.20
    Activations Density 0.013%

    No Known Activations