© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    phrases related to the idiom "the final straw"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "final straw."

    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
    rot
    -0.67
     Reports
    -0.65
     performing
    -0.65
     Mode
    -0.64
    kaya
    -0.64
    gression
    -0.64
     Sev
    -0.63
    Master
    -0.62
    ov
    -0.62
     LOC
    -0.62
    POSITIVE LOGITS
     straw
    4.66
     Straw
    2.45
     hay
    0.96
     tul
    0.89
     feather
    0.87
     strawberry
    0.87
     grass
    0.84
     mud
    0.84
     strawberries
    0.83
    utherland
    0.83
    Activations Density 0.020%

    No Known Activations