INDEX

Explanations

references to economic indicators, specifically focusing on price-related terms

oai_token-act-pair · gpt-3.5-turbo

mentioning of prices and their variations

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

irlf

-0.99

eworks

-0.94

estern

-0.88

mbuds

-0.87

orough

-0.87

 Schne

-0.82

andestine

-0.75

ocamp

-0.75

ullivan

-0.74

 Panzer

-0.73

POSITIVE LOGITS

gou

1.08

 prices

1.04

 inflation

0.96

 premiums

0.95

 fluctuations

0.92

 volatility

0.92

 price

0.90

 fluct

0.89

 differential

0.87

 deflation

0.84

Activations Density 0.033%

references to economic indicators, specifically focusing on price-related terms

mentioning of prices and their variations

No Comments

No Known Activations