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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9477
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for words related to layers or boundaries of objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the "outer" layers or boundaries of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essors
    -0.78
    inators
    -0.74
    inatory
    -0.74
    inator
    -0.74
    netflix
    -0.73
    Pitt
    -0.72
    bley
    -0.71
    anwhile
    -0.71
    HCR
    -0.71
    utes
    -0.70
    POSITIVE LOGITS
    most
    1.31
    wear
    1.01
     casing
    0.85
     circumference
    0.85
    worldly
    0.84
    borough
    0.84
     diameter
    0.83
     garments
    0.79
     bounds
    0.79
     extrem
    0.77
    Activations Density 0.012%

    No Known Activations