INDEX

Explanations

dates and locations from news articles

oai_token-act-pair · gpt-3.5-turbo

instances of slashes or parentheses within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 prey

-0.74

 disgu

-0.70

 record

-0.69

 inqu

-0.69

 records

-0.67

 predators

-0.66

 advert

-0.66

rug

-0.66

 accus

-0.66

 infiltr

-0.65

POSITIVE LOGITS

AFP

1.09

Flickr

1.08

Courtesy

1.08

Getty

1.07

Bloomberg

1.01

ËĪ

0.94

CBC

0.94

Staff

0.90

jon

0.90

via

0.89

Activations Density 0.028%

dates and locations from news articles

instances of slashes or parentheses within the text

No Comments

No Known Activations