© 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. 9352
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and execution of various activities or strategies

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    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
    here
    -0.82
    lass
    -0.74
    reviewed
    -0.71
    =>
    -0.69
    cakes
    -0.68
    sburgh
    -0.68
    ipedia
    -0.67
    ilight
    -0.67
    packing
    -0.67
    ãĥĺ
    -0.66
    POSITIVE LOGITS
     exception
    1.62
     intention
    1.50
     caveat
    1.43
     help
    1.41
     aim
    1.34
     assistance
    1.31
     intent
    1.29
     aid
    1.21
     expectation
    1.17
     blessing
    1.10
    Activations Density 0.140%

    No Known Activations