© 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. 0-RES-JB
    11. 4047
    Prev
    Next
    INDEX
    Explanations

    questions involving decision-making and moral dilemmas

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "should," indicating ethical or prescriptive considerations

    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
    esters
    -0.64
     pie
    -0.61
     elusive
    -0.60
     witness
    -0.59
     hosp
    -0.58
     anonymously
    -0.58
     fraternity
    -0.58
     trace
    -0.56
     mystery
    -0.56
     investigators
    -0.56
    POSITIVE LOGITS
     Should
    3.44
    Should
    2.83
    should
    2.28
     SHOULD
    2.09
     should
    1.44
     Would
    1.41
     Might
    1.39
     Could
    1.38
     Shall
    1.36
     Wouldn
    1.32
    Activations Density 0.013%

    No Known Activations