INDEX

Explanations

phrases related to methods, processes, or instructions

oai_token-act-pair · gpt-3.5-turbo

repetitive conjunctions and phrases related to questioning circumstances or conditions

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

IRE

-0.67

 Roller

-0.63

Gry

-0.62

 Kirin

-0.59

 Mens

-0.59

 Sixth

-0.58

 Swan

-0.57

 Pyramid

-0.56

Yog

-0.56

Wan

-0.56

POSITIVE LOGITS

why

1.04

rogens

1.02

rogen

0.94

abouts

0.93

WHY

0.87

anwhile

0.84

 whence

0.83

tymology

0.82

why

0.80

 exactly

0.78

Activations Density 0.067%

phrases related to methods, processes, or instructions

repetitive conjunctions and phrases related to questioning circumstances or conditions

No Comments

No Known Activations