INDEX

Explanations

instances of turning around or changing direction

oai_token-act-pair · gpt-3.5-turbo

phrases related to turning or changing direction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enegger

-0.66

è¦ļéĨĴ

-0.65

lain

-0.65

inks

-0.61

jay

-0.61

 ceilings

-0.61

 confir

-0.60

 indemn

-0.59

erness

-0.58

accompan

-0.56

POSITIVE LOGITS

 tide

0.83

emort

0.81

 abruptly

0.79

wagen

0.78

 fortunes

0.76

ï¸

0.75

 âĸº

0.72

UTE

0.69

quickShipAvailable

0.68

EGA

0.67

Activations Density 0.064%

instances of turning around or changing direction

phrases related to turning or changing direction

No Comments

No Known Activations