© 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. 8-RES-JB
    11. 6238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a decision or judgment based on certain criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "based on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.81
    bats
    -0.77
    ura
    -0.74
    Sport
    -0.71
    Lab
    -0.71
    zon
    -0.70
    Forge
    -0.69
    flush
    -0.68
    Bit
    -0.68
    Daddy
    -0.66
    POSITIVE LOGITS
     behalf
    0.99
     principles
    0.98
     assumption
    0.93
     assumptions
    0.88
     hears
    0.87
     principle
    0.85
     observation
    0.84
     sheer
    0.84
     conjecture
    0.82
     observations
    0.80
    Activations Density 0.095%

    No Known Activations