© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6834
    Prev
    Next
    INDEX
    Explanations

    potential areas of growth and improvement, especially related to work and performance

    oai_token-act-pair · gpt-3.5-turbo

    references to quantitative measures and values related to performance or benefits

    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
    Same
    -0.53
    ?,
    -0.53
     Exactly
    -0.52
    Enabled
    -0.52
    jab
    -0.52
    urion
    -0.51
     and
    -0.49
     Slightly
    -0.49
    ateurs
    -0.49
    oft
    -0.48
    POSITIVE LOGITS
    cellaneous
    0.76
    etooth
    0.60
    lihood
    0.60
    zbollah
    0.55
     importantly
    0.53
     overall
    0.53
    ollah
    0.52
     humanitarian
    0.51
     standby
    0.51
     gloss
    0.50
    Activations Density 1.091%

    No Known Activations