© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16831
    Prev
    Next
    INDEX
    Explanations

    instances of words related to duties and obligations

    oai_token-act-pair · gpt-3.5-turbo

    references to duties and obligations

    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
     Tun
    -0.72
    aneous
    -0.70
    bay
    -0.69
    eb
    -0.68
    adel
    -0.65
     anecdotal
    -0.64
    bit
    -0.62
    Bay
    -0.62
    aneously
    -0.62
    cise
    -0.62
    POSITIVE LOGITS
     responsibilities
    1.28
     obligations
    1.03
    afety
    0.94
    urden
    0.93
    ngth
    0.91
    uties
    0.90
     duties
    0.88
     citiz
    0.86
     arrang
    0.84
    ibling
    0.84
    Activations Density 0.011%

    No Known Activations