© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 4117
    Prev
    Next
    INDEX
    Explanations

    phrases related to high-ranking or influential individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "top" associated with rankings or leadership roles

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

    No Comments

    Negative Logits
    ibaba
    -0.74
    cosystem
    -0.73
    REG
    -0.71
     Interstellar
    -0.70
    eries
    -0.70
    Frames
    -0.68
     Syndrome
    -0.68
     Wilde
    -0.68
    Interstitial
    -0.66
     Retro
    -0.66
    POSITIVE LOGITS
     aide
    1.18
     diplomat
    1.03
     aides
    1.02
     staffer
    0.98
     prosecutor
    0.98
     adviser
    0.89
     brass
    0.89
     minister
    0.87
     secret
    0.87
     negotiator
    0.87
    Activations Density 0.054%

    No Known Activations