INDEX

Explanations

phrases related to exploration and adventure

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "explore" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

fight

-0.71

fixed

-0.70

jud

-0.67

ivari

-0.66

enta

-0.66

lat

-0.62

corn

-0.62

wa

-0.62

ĪĴ

-0.61

die

-0.61

POSITIVE LOGITS

ĸļ

0.95

ibility

0.85

vier

0.84

ibilities

0.83

ationally

0.80

 Explore

0.79

prising

0.79

Ô

0.78

çīĪ

0.76

ONSORED

0.74

Activations Density 0.023%

phrases related to exploration and adventure

occurrences of the word "explore" in various contexts

No Comments

No Known Activations