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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10029
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "too" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express limitations or excessive amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.78
    scribe
    -0.68
    iamond
    -0.67
    USS
    -0.64
    ffer
    -0.63
    ief
    -0.63
    clud
    -0.62
    FOX
    -0.61
    amines
    -0.61
    ciation
    -0.61
    POSITIVE LOGITS
    too
    2.03
     too
    1.88
     Too
    1.87
    Too
    1.83
     insufficient
    1.41
     overly
    1.16
     excessively
    1.13
     unnecessarily
    1.09
     careless
    1.07
     inadequate
    1.06
    Activations Density 0.172%

    No Known Activations