INDEX

Explanations

phrases related to a specific telecommunication company

oai_token-act-pair · gpt-3.5-turbo

mentions of the company AT&T

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

perse

-0.87

aceutical

-0.72

clean

-0.71

released

-0.70

uyomi

-0.68

theless

-0.65

reviewed

-0.64

 Notting

-0.63

 inhab

-0.62

ppelin

-0.60

POSITIVE LOGITS

AT

0.97

tiny

0.96

mega

0.93

ARI

0.92

Ms

0.91

TL

0.89

OM

0.88

EMENT

0.87

OC

0.86

AP

0.85

Activations Density 0.013%

phrases related to a specific telecommunication company

mentions of the company AT&T

No Comments

No Known Activations