© 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. 0-RES-JB
    11. 17942
    Prev
    Next
    INDEX
    Explanations

    instances of objects or structures that are intentionally created with a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "designed"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apsed
    -0.68
    ences
    -0.66
    merga
    -0.66
     Anarchy
    -0.65
     pts
    -0.61
     Dep
    -0.61
    ã
    -0.60
    marg
    -0.59
    rieving
    -0.57
    eph
    -0.57
    POSITIVE LOGITS
     designed
    3.33
    designed
    2.65
     Designed
    2.21
     intended
    2.00
     aimed
    1.81
     engineered
    1.76
     devised
    1.74
     programmed
    1.64
     crafted
    1.64
     geared
    1.62
    Activations Density 0.028%

    No Known Activations