INDEX

Explanations

advertisements within a text

oai_token-act-pair · gpt-3.5-turbo

instances of advertisements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vain

-0.78

 contingency

-0.77

 bunk

-0.75

clus

-0.74

 sacr

-0.73

 explor

-0.70

 pred

-0.70

 planned

-0.70

 marsh

-0.69

 corpor

-0.68

POSITIVE LOGITS

Advertisement

1.37

 Advertisement

1.12

advertisement

1.01

});

0.93

taboola

0.90

ertodd

0.90

advertising

0.83

Images

0.83

Credit

0.82

 Continue

0.80

Activations Density 0.013%

advertisements within a text

instances of advertisements

No Comments

No Known Activations