© 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. 4-RES-JB
    11. 15425
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arguably" in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that present a claim or opinion in a speculative manner

    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
    nen
    -0.77
    ters
    -0.70
    aeus
    -0.69
    ysis
    -0.67
    spr
    -0.67
    letter
    -0.67
    eries
    -0.66
    chens
    -0.64
     Bowl
    -0.64
    raged
    -0.63
    POSITIVE LOGITS
     metic
    0.92
     unemploy
    0.76
     deserved
    0.76
     underrated
    0.72
    è¦
    0.70
     overlooked
    0.69
    ©¶æ¥µ
    0.69
     conduc
    0.68
    interstitial
    0.68
     disadvant
    0.65
    Activations Density 0.009%

    No Known Activations