© 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. 0-RES-JB
    11. 22341
    Prev
    Next
    INDEX
    Explanations

    words related to superpowers or exceptional abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "super" as a prefix or descriptor

    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
     Frie
    -0.76
     Rasm
    -0.72
    FFER
    -0.71
    nered
    -0.71
    Days
    -0.71
    gaard
    -0.70
    Dialogue
    -0.69
    oven
    -0.69
     Erd
    -0.69
    nell
    -0.68
    POSITIVE LOGITS
     super
    3.39
    super
    2.45
     Super
    2.04
     SUPER
    2.04
    Super
    2.02
     supers
    1.54
     mega
    1.49
     ultra
    1.40
     superpower
    1.34
     uber
    1.33
    Activations Density 0.018%

    No Known Activations