© 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. 2-RES-JB
    11. 24131
    Prev
    Next
    INDEX
    Explanations

    urgent and important messages or actions that need to be taken

    oai_token-act-pair · gpt-3.5-turbo

    the term "MUST" and related phrases indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.73
     Gw
    -0.72
    anka
    -0.70
     Vish
    -0.69
     Bhar
    -0.68
     Hamp
    -0.65
     Jung
    -0.63
     Chak
    -0.63
     Gandhi
    -0.63
    alities
    -0.62
    POSITIVE LOGITS
     WATCH
    0.97
     MUST
    0.97
    ARD
    0.94
    ATCH
    0.93
    ICLE
    0.89
    HAEL
    0.88
    VEL
    0.87
     obey
    0.87
    ORTS
    0.86
    ELY
    0.84
    Activations Density 0.003%

    No Known Activations