INDEX

Explanations

health-related terms or entities

oai_token-act-pair · gpt-3.5-turbo

references to health organizations and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

unci

-0.76

oÄŁ

-0.74

 Logged

-0.69

inventoryQuantity

-0.69

 Guatem

-0.65

ãĥĪ

-0.63

itive

-0.62

 Adin

-0.61

auc

-0.60

 Ramos

-0.60

POSITIVE LOGITS

 Revenge

0.68

 Mutual

0.67

deen

0.64

 dominion

0.63

vation

0.62

 Quest

0.61

 philosophy

0.61

 Dictionary

0.60

 emancipation

0.60

 dividend

0.59

Activations Density 0.193%

health-related terms or entities

references to health organizations and programs

No Comments

No Known Activations