© 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. 9-RES-JB
    11. 15695
    Prev
    Next
    INDEX
    Explanations

    words related to rebuilding, repairing, and revitalizing

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to recovery and rebuilding processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oS
    -0.76
    WARNING
    -0.74
    nesty
    -0.73
    ĸļ
    -0.72
    swer
    -0.70
    Override
    -0.69
    aterasu
    -0.69
    binding
    -0.69
    rance
    -0.69
    asking
    -0.69
    POSITIVE LOGITS
     damaged
    1.34
     depleted
    1.22
     battered
    1.20
     shattered
    1.13
     crumbling
    1.08
     ravaged
    1.06
     neglected
    1.06
     devastated
    1.04
     wounds
    1.03
     stalled
    1.03
    Activations Density 0.347%

    No Known Activations