© 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. 17235
    Prev
    Next
    INDEX
    Explanations

    verbs followed by specific medical procedures or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "has" in various contexts, indicating an ongoing state or action

    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
     Guess
    -0.70
     Saying
    -0.67
    bery
    -0.63
    Give
    -0.62
     Loading
    -0.62
     Expect
    -0.60
     Interview
    -0.60
     Pair
    -0.59
     Believe
    -0.59
     Finish
    -0.59
    POSITIVE LOGITS
     been
    1.36
     existed
    1.36
     become
    1.28
     undergone
    1.26
     arisen
    1.20
    been
    1.17
     evolved
    1.15
     emerged
    1.15
     flourished
    1.13
     traditionally
    1.11
    Activations Density 0.159%

    No Known Activations