© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    financial terms and motivational expressions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal beliefs and values about love and integrity

    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
     retracted
    -0.75
    quished
    -0.75
     hastily
    -0.72
     censored
    -0.72
     aborted
    -0.72
     resumed
    -0.70
     charred
    -0.69
     incrim
    -0.69
     discontinued
    -0.67
     staggered
    -0.67
    POSITIVE LOGITS
     Excellence
    1.02
     Values
    0.96
     Integrity
    0.95
    cellence
    0.93
    Ultimately
    0.93
     fostering
    0.89
     That
    0.88
     Whether
    0.87
     Ens
    0.86
     Creating
    0.86
    Activations Density 0.442%

    No Known Activations