© 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. 18002
    Prev
    Next
    INDEX
    Explanations

    proper names or acronyms that include the letters "Sus"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Sus" and its variations

    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
    lite
    -0.68
    RAFT
    -0.67
    illet
    -0.64
    lift
    -0.64
    LD
    -0.63
    fters
    -0.63
     carve
    -0.63
    raft
    -0.63
    Draft
    -0.62
    ale
    -0.62
    POSITIVE LOGITS
     Sus
    4.03
    Sus
    2.84
     sus
    1.54
     Suz
    1.31
     unsus
    1.07
     suspects
    1.03
     Alleg
    1.02
     Innocent
    1.02
     Hus
    0.98
     Sebast
    0.98
    Activations Density 0.014%

    No Known Activations