INDEX

Explanations

phrases related to politics and government

oai_token-act-pair · gpt-3.5-turbo

specific political actions and statements made by leaders

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

selves

-0.97

 selves

-0.78

 Sensor

-0.72

scan

-0.72

âĵĺ

-0.68

 mats

-0.67

geries

-0.66

Origin

-0.65

[];

-0.64

DragonMagazine

-0.63

POSITIVE LOGITS

 himself

1.30

 Cabinet

1.06

 aides

1.02

his

1.01

 reelection

1.01

 veto

0.98

 diplomacy

0.98

 Himself

0.94

 unilaterally

0.94

 pard

0.92

Activations Density 0.799%

phrases related to politics and government

specific political actions and statements made by leaders

No Comments

No Known Activations