INDEX

Explanations

health-related terms, specifically focusing on diseases and their associated risks

oai_token-act-pair · gpt-3.5-turbo

terms related to health risks and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

selage

-0.72

htaking

-0.72

 vendor

-0.72

ãĥ¼ãĥĨãĤ£

-0.71

ãĥ£

-0.68

xtap

-0.68

orate

-0.65

ãĥ³ãĤ¸

-0.64

secut

-0.63

ãĤ©

-0.63

POSITIVE LOGITS

 syndrome

1.06

 Symptoms

0.99

 symptoms

0.96

 Syndrome

0.90

ptoms

0.88

associated

0.86

 mell

0.84

 disorders

0.83

ause

0.83

 inflammation

0.81

Activations Density 0.180%

health-related terms, specifically focusing on diseases and their associated risks

terms related to health risks and medical conditions

No Comments

No Known Activations