© 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. 10223
    Prev
    Next
    INDEX
    Explanations

    mentions of superhuman powers and abilities

    oai_token-act-pair · gpt-3.5-turbo

    elements related to advanced technology and superpowers in a narrative context

    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
    udeb
    -0.82
    ardy
    -0.81
    displayText
    -0.79
    sale
    -0.78
    iscopal
    -0.78
    Reporting
    -0.73
    emouth
    -0.72
    Pitt
    -0.70
    isky
    -0.69
     Cosponsors
    -0.69
    POSITIVE LOGITS
     teleportation
    1.30
     immortality
    1.25
     clones
    1.24
     Ultron
    1.21
     implants
    1.20
     Krypt
    1.19
     superhuman
    1.17
     dimensional
    1.16
     psi
    1.15
     cloning
    1.13
    Activations Density 0.690%

    No Known Activations