© 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. 10-RES-JB
    11. 10581
    Prev
    Next
    INDEX
    Explanations

    words related to rebuilding, reconstructing, reinventing, and redesigning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rebuilding or rebooting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPA
    -0.64
    ppe
    -0.61
    holders
    -0.60
    holes
    -0.59
     ASA
    -0.59
    cius
    -0.58
    erry
    -0.58
     disobedience
    -0.58
    chain
    -0.58
    QB
    -0.57
    POSITIVE LOGITS
    ilitation
    0.90
    naissance
    0.89
    issance
    0.86
    ilitating
    0.85
    spective
    0.77
    itory
    0.76
     rejuven
    0.75
    eco
    0.74
     Tycoon
    0.71
    itect
    0.70
    Activations Density 0.079%

    No Known Activations