INDEX

Explanations

phrases related to historical events and figures

oai_token-act-pair · gpt-3.5-turbo

specific proposals or recommendations regarding individual or group actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

(@

-0.97

ï¸ı

-0.89

bnb

-0.88

 WATCH

-0.87

-0.83

 GoPro

-0.82

 Marketplace

-0.81

 Awakens

-0.81

 Xiaomi

-0.80

 Lyft

-0.77

POSITIVE LOGITS

 postwar

1.12

 Soviet

0.95

 hereditary

0.95

 wartime

0.90

 arist

0.89

 seventeen

0.89

Soviet

0.89

 forty

0.88

 eighty

0.87

 seventy

0.86

Activations Density 1.489%

phrases related to historical events and figures

specific proposals or recommendations regarding individual or group actions

No Comments

No Known Activations