© 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. 8-RES-JB
    11. 23546
    Prev
    Next
    INDEX
    Explanations

    words related to pretentiousness

    oai_token-act-pair · gpt-3.5-turbo

    the word "pret" and its variants, suggesting a focus on pretentiousness or pretense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.77
     [|
    -0.73
    SHIP
    -0.72
    20439
    -0.72
     "$:/
    -0.67
     GOODMAN
    -0.65
    sbm
    -0.64
    士
    -0.63
    tips
    -0.61
    stocks
    -0.61
    POSITIVE LOGITS
    entious
    1.34
    ensions
    1.33
    reatment
    1.28
    ension
    1.27
    reating
    1.25
    zel
    1.18
    reated
    1.15
    rial
    1.12
    inent
    1.07
    ournament
    1.01
    Activations Density 0.027%

    No Known Activations