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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24151
    Prev
    Next
    INDEX
    Explanations

    words related to infrastructure and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to limitations and barriers

    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
    nesday
    -0.58
     Eleven
    -0.55
     Noon
    -0.54
     Pretty
    -0.53
    Pretty
    -0.52
     Quinn
    -0.52
    Monday
    -0.51
    five
    -0.51
     Wonderful
    -0.51
     101
    -0.50
    POSITIVE LOGITS
     costly
    0.78
     pathogens
    0.75
     populations
    0.75
     adversaries
    0.73
     oneself
    0.72
     spouses
    0.71
     neighborhoods
    0.71
     ceilings
    0.71
     neighbourhoods
    0.70
     environments
    0.70
    Activations Density 1.090%

    No Known Activations