INDEX

Explanations

medical and health-related risk factors or implications

oai_token-act-pair · gpt-3.5-turbo

terms related to risk factors and their associations with health issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

elf

-0.85

Nap

-0.73

issance

-0.72

ilver

-0.71

zeb

-0.70

 Seasons

-0.70

Series

-0.69

Bit

-0.68

 Remastered

-0.68

æ©Ł

-0.67

POSITIVE LOGITS

 factors

0.94

 factor

0.86

 allele

0.84

 proble

0.79

 risk

0.77

 risks

0.77

 horm

0.77

 hormones

0.76

 hazards

0.75

 alle

0.74

Activations Density 0.021%

medical and health-related risk factors or implications

terms related to risk factors and their associations with health issues

No Comments

No Known Activations