INDEX

Explanations

words related to natural resources, specifically focusing on coal, oil, and gas

oai_token-act-pair · gpt-3.5-turbo

phrases related to water and gas resources

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

Reviewer

-0.84

iors

-0.79

:{

-0.75

FK

-0.74

 condem

-0.72

Own

-0.71

cknow

-0.71

ortmund

-0.71

edIn

-0.70

hower

-0.70

POSITIVE LOGITS

 minerals

1.05

 electroly

0.92

 beverage

0.91

 salt

0.89

 drink

0.89

 nitrogen

0.88

 oxygen

0.87

 sulph

0.86

 mineral

0.85

 beverages

0.85

Activations Density 0.281%

words related to natural resources, specifically focusing on coal, oil, and gas

phrases related to water and gas resources

No Comments

No Known Activations