INDEX

Explanations

phrases indicating physical position or movement over something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "over."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illary

-0.88

Â¯Â¯Â¯Â¯

-0.73

UE

-0.72

 Lauder

-0.71

uum

-0.65

arium

-0.64

UES

-0.63

ãĥ¼ãĥĨãĤ£

-0.62

ãĥ¼ãĥĨ

-0.60

egal

-0.60

POSITIVE LOGITS

hang

1.11

loading

1.01

drive

0.97

tones

0.95

lord

0.93

lay

0.92

hung

0.87

haul

0.84

kill

0.83

mast

0.83

Activations Density 0.081%

phrases indicating physical position or movement over something

instances of the word "over."

No Comments

No Known Activations