© 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. 7-RES-JB
    11. 2212
    Prev
    Next
    INDEX
    Explanations

    The main thing Neuron 4 is looking for is words related to superhuman abilities or powers, especially those involving psychic or supernatural elements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to supernatural or psychic abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.88
    Ô
    -0.86
     Playoff
    -0.85
    Lean
    -0.83
     Coverage
    -0.82
    Case
    -0.81
    Reporting
    -0.77
    Brook
    -0.77
     Yard
    -0.77
    Contribut
    -0.75
    POSITIVE LOGITS
     psychic
    1.24
     teleportation
    1.22
     humanoid
    1.17
     sorcerer
    1.16
     sorce
    1.15
     teleport
    1.11
     beings
    1.10
     orbs
    1.10
     sorcery
    1.10
     Sorce
    1.09
    Activations Density 0.658%

    No Known Activations