INDEX

Explanations

the word "way" used to indicate a method, approach, or direction

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of methods or approaches

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

cius

-0.76

tyr

-0.71

 blockers

-0.66

una

-0.66

urg

-0.65

oft

-0.64

agus

-0.61

 Ples

-0.61

erville

-0.60

psey

-0.60

POSITIVE LOGITS

fare

0.85

forward

0.79

 NETWORK

0.76

é¾įåĸļå£«

0.75

CHO

0.70

finding

0.69

rait

0.66

ward

0.64

 THEY

0.60

 whenever

0.60

Activations Density 0.019%

the word "way" used to indicate a method, approach, or direction

phrases that emphasize the concept of methods or approaches

No Comments

No Known Activations