© 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. 20525
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe a level of clarity or frankness in communication

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate clarity, openness, specificity, and selectivity in communication

    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
    ools
    -0.60
    odes
    -0.59
     stub
    -0.57
    ancies
    -0.57
    ä½ľ
    -0.55
    ãĥ¼ãĥĨãĤ£
    -0.55
    ampa
    -0.54
    Stand
    -0.54
     Bridges
    -0.52
     Explosion
    -0.51
    POSITIVE LOGITS
     about
    1.36
    about
    1.20
     ABOUT
    1.14
     enough
    1.11
     About
    0.99
     regarding
    0.98
    ially
    0.89
    enough
    0.89
    cerning
    0.88
    ently
    0.83
    Activations Density 0.220%

    No Known Activations