INDEX

Explanations

phrases indicating rationale or justification

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the justification or rationale behind statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chron

-0.75

chin

-0.68

tein

-0.68

 Carbuncle

-0.65

inav

-0.64

semble

-0.64

eg

-0.62

ega

-0.61

 Warcraft

-0.60

 ages

-0.60

POSITIVE LOGITS

why

1.41

WHY

1.19

why

1.17

abl

1.12

Why

0.94

Why

0.88

 justifying

0.84

pointers

0.81

Reviewer

0.80

 rationale

0.78

Activations Density 0.037%

phrases indicating rationale or justification

phrases emphasizing the justification or rationale behind statements

No Comments

No Known Activations