INDEX

Explanations

phrases related to health risks

oai_token-act-pair · gpt-3.5-turbo

terms related to risk factors associated with health conditions

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

issance

-0.88

utra

-0.72

elf

-0.71

zeb

-0.68

 Dick

-0.67

 stead

-0.67

hire

-0.65

ilver

-0.64

 Crane

-0.63

orld

-0.63

POSITIVE LOGITS

 factors

0.90

 allele

0.85

ogenic

0.80

 factor

0.78

ogens

0.77

 Factors

0.76

 mortality

0.75

 chromos

0.75

ologically

0.74

 behaviors

0.73

Activations Density 0.049%

phrases related to health risks

terms related to risk factors associated with health conditions

No Comments

No Known Activations