INDEX

Explanations

the phrase "by the way"

oai_token-act-pair · gpt-3.5-turbo

phrases that include the expression "by the way."

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

ĸļ

-0.83

incinn

-0.77

¥ŀ

-0.73

uster

-0.72

 nurs

-0.70

anmar

-0.70

 corrid

-0.68

 tremend

-0.68

usters

-0.67

ifer

-0.65

POSITIVE LOGITS

ward

0.82

WARD

0.74

sey

0.71

fare

0.70

points

0.68

point

0.67

Bonus

0.67

chery

0.66

KEY

0.65

 Pyth

0.65

Activations Density 0.013%

the phrase "by the way"

phrases that include the expression "by the way."

No Comments

No Known Activations