© 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 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. 8-RES-JB
    11. 10947
    Prev
    Next
    INDEX
    Explanations

    verbs related to complete removal or destruction

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the act of erasing or eliminating

    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
    fman
    -0.91
    ensical
    -0.77
    egal
    -0.75
     Sop
    -0.73
    anooga
    -0.72
    edly
    -0.70
    yrinth
    -0.70
    ruciating
    -0.69
    xual
    -0.68
    gomery
    -0.67
    POSITIVE LOGITS
     wipes
    0.88
     wiping
    0.87
     awa
    0.85
     wiped
    0.84
     ashore
    0.83
     goodbye
    0.83
     wipe
    0.83
    out
    0.81
    stakes
    0.78
     off
    0.76
    Activations Density 0.036%

    No Known Activations