© 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. 952
    Prev
    Next
    INDEX
    Explanations

    phrases or statements that are downplaying or minimizing a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statements of significance and the themes of innocence and exaggeration

    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
    ais
    -0.75
     Sabha
    -0.72
    Ku
    -0.71
    azel
    -0.68
    arov
    -0.68
    raved
    -0.68
    oving
    -0.67
    aldi
    -0.66
    abase
    -0.66
     Nanto
    -0.65
    POSITIVE LOGITS
     understatement
    1.14
    ibia
    0.75
    igible
    0.75
    sson
    0.73
    terday
    0.71
     exaggeration
    0.70
     attRot
    0.67
     probabilities
    0.66
     Osw
    0.66
    swer
    0.66
    Activations Density 0.013%

    No Known Activations