INDEX

Explanations

phrases containing the word "only"

oai_token-act-pair · gpt-3.5-turbo

the phrase "not only," which suggests the inclusion of additional information or ideas

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

»Ĵ

-0.79

 Hanson

-0.70

 Nanto

-0.70

 Fallen

-0.67

ĳå£«

-0.65

lain

-0.65

 largeDownload

-0.63

 Bers

-0.62

glomer

-0.61

insert

-0.61

POSITIVE LOGITS

oped

0.67

ifiable

0.64

obe

0.64

othing

0.62

onew

0.61

cki

0.61

tem

0.60

 verbally

0.60

 interested

0.60

 physically

0.59

Activations Density 0.027%

phrases containing the word "only"

the phrase "not only," which suggests the inclusion of additional information or ideas

No Comments

No Known Activations