INDEX

Explanations

phrases indicating a strong emphasis or assertion

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

WARD

-0.67

emis

-0.64

Veter

-0.60

 Prepar

-0.60

PRESS

-0.59

Acknowled

-0.59

 Targ

-0.59

Tax

-0.58

Luck

-0.58

èĪ

-0.58

POSITIVE LOGITS

cher

0.91

chers

0.85

ched

0.80

ching

0.79

 fateful

0.75

 lasted

0.73

 damned

0.71

 pesky

0.71

ÅĤ

0.66

 fundament

0.63

Activations Density 0.124%

phrases indicating a strong emphasis or assertion

the word "that" in various contexts

No Comments

No Known Activations