INDEX

Explanations

political affiliations in statements

oai_token-act-pair · gpt-3.5-turbo

references to political affiliations, particularly conservatives and liberals

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

Delivery

-0.74

 Bulldogs

-0.70

Owner

-0.64

BY

-0.63

 Kuala

-0.63

Ship

-0.62

inventoryQuantity

-0.59

rawdownloadcloneembedreportprint

-0.58

 Pocket

-0.57

Appearance

-0.57

POSITIVE LOGITS

ervatives

1.41

ervative

1.35

 rejoice

0.97

paces

0.96

 everywhere

0.92

aurus

0.85

 alike

0.85

pace

0.85

 despise

0.78

 argue

0.78

Activations Density 0.070%

political affiliations in statements

references to political affiliations, particularly conservatives and liberals

No Comments

No Known Activations