© 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. 1-RES-JB
    11. 14323
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "subjected" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "subjected" and its variations, indicating experiences of hardship or oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grape
    -0.69
     Clover
    -0.66
     Fargo
    -0.66
     direction
    -0.65
     Cic
    -0.63
     Pis
    -0.63
     Alps
    -0.62
     Helsinki
    -0.62
     Plan
    -0.61
    fly
    -0.61
    POSITIVE LOGITS
     subjected
    1.16
    ĸļ
    0.98
    ynamic
    0.85
    Reviewer
    0.84
    racuse
    0.83
    soever
    0.82
    ombat
    0.82
     describ
    0.81
     challeng
    0.81
    quished
    0.80
    Activations Density 0.007%

    No Known Activations