INDEX

Explanations

large numerical quantities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

quantitative references to large numbers or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

venge

-0.67

inventoryQuantity

-0.67

 envy

-0.65

Dialogue

-0.64

ufact

-0.63

unct

-0.61

itta

-0.61

 Prelude

-0.61

 Redemption

-0.61

ourage

-0.60

POSITIVE LOGITS

 hectares

0.96

 pounds

0.95

 acres

0.93

lbs

0.92

lbs

0.92

lb

0.90

sq

0.89

 tonnes

0.88

 kilograms

0.87

 miles

0.86

Activations Density 0.117%

large numerical quantities mentioned in the text

quantitative references to large numbers or statistics

No Comments

No Known Activations