© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 8344
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct action or instruction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Direct"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bubble
    -0.76
    phia
    -0.74
    uffle
    -0.72
    Angelo
    -0.68
     pearl
    -0.68
    ulum
    -0.67
     sailor
    -0.66
     suit
    -0.66
     adventurer
    -0.65
    IENCE
    -0.65
    POSITIVE LOGITS
     Direct
    3.66
    Direct
    3.45
    direct
    2.77
     DIRECT
    2.02
     direct
    1.80
     indirect
    1.54
    directed
    1.44
    irect
    1.39
     Directions
    1.26
     directed
    1.26
    Activations Density 0.030%

    No Known Activations