© 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. 4-RES-JB
    11. 22235
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the lack of necessity or requirement for something to be done or used

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a lack of necessity or need

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

    No Comments

    Negative Logits
    catentry
    -0.76
    uesday
    -0.71
    Pacific
    -0.71
    yrinth
    -0.70
    geist
    -0.68
     Millennium
    -0.68
    slow
    -0.68
    culosis
    -0.67
    favorite
    -0.65
    adder
    -0.63
    POSITIVE LOGITS
     anymore
    1.33
     nor
    1.06
     whatsoever
    0.92
     interruption
    0.89
     necessarily
    0.88
    lessly
    0.82
     anywhere
    0.79
     anything
    0.75
     any
    0.74
     hassle
    0.73
    Activations Density 0.099%

    No Known Activations