© 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. 18778
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal preferences or enjoyment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of preference or liking

    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
    arta
    -0.80
    tek
    -0.72
    irrel
    -0.71
    krit
    -0.70
    cession
    -0.69
    ilion
    -0.69
    inary
    -0.68
    Login
    -0.68
    INAL
    -0.64
    PATH
    -0.64
    POSITIVE LOGITS
     seeing
    1.00
     experimenting
    0.91
     watching
    0.91
     surprises
    0.88
     interacting
    0.87
     hearing
    0.87
     having
    0.86
     to
    0.86
     talking
    0.79
    ably
    0.78
    Activations Density 0.075%

    No Known Activations