INDEX

Explanations

phrases indicating something extends beyond a certain limit or expectation

oai_token-act-pair · gpt-3.5-turbo

phrases or concepts that indicate exceeding limits or boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

CCC

-0.70

 Nanto

-0.70

pei

-0.67

SPONSORED

-0.66

soon

-0.65

utenberg

-0.65

uyomi

-0.63

é¾įåĸļå£«

-0.63

cc

-0.63

edy

-0.63

POSITIVE LOGITS

 superficial

0.84

 cosmetic

0.81

 caring

0.76

 fixing

0.71

 monetary

0.68

 mere

0.66

 aesthetics

0.65

 merely

0.64

 addressing

0.63

 cosmetics

0.63

Activations Density 0.106%

phrases indicating something extends beyond a certain limit or expectation

phrases or concepts that indicate exceeding limits or boundaries

No Comments

No Known Activations