© 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. 16561
    Prev
    Next
    INDEX
    Explanations

    questions asking for definitions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    question phrases that start with "What is."

    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
    lator
    -0.81
    iless
    -0.78
    devices
    -0.78
    lems
    -0.74
    scenes
    -0.73
    geoning
    -0.71
    ared
    -0.71
    ties
    -0.71
    owan
    -0.70
    asers
    -0.70
    POSITIVE LOGITS
     happening
    1.01
     meant
    0.89
     wrong
    0.88
     your
    0.82
     YOUR
    0.76
     it
    0.74
     going
    0.72
     yours
    0.72
     Wrong
    0.70
     occurring
    0.70
    Activations Density 0.044%

    No Known Activations