© 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. 21401
    Prev
    Next
    INDEX
    Explanations

    verbs following the phrase "good at"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "good at" followed by various activities or skills

    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
    eful
    -0.80
    iments
    -0.71
    emn
    -0.70
    enic
    -0.67
    isite
    -0.67
    imentary
    -0.66
    Visit
    -0.65
    aeus
    -0.65
    uria
    -0.65
    ish
    -0.65
    POSITIVE LOGITS
     predicting
    1.43
     manipulating
    1.35
     detecting
    1.34
     communicating
    1.28
     figuring
    1.28
     spotting
    1.26
     navigating
    1.26
     estimating
    1.24
     adapting
    1.23
     recognizing
    1.22
    Activations Density 0.108%

    No Known Activations