INDEX

Explanations

medical imaging related terms, specifically X-rays

oai_token-act-pair · gpt-3.5-turbo

references to X-rays and their implications in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 finish

-0.67

 contingency

-0.65

 crossover

-0.63

 Success

-0.63

 role

-0.62

AG

-0.62

 semif

-0.62

Suc

-0.61

 polit

-0.61

 Lower

-0.61

POSITIVE LOGITS

rays

4.56

ray

1.68

RAY

1.62

 rays

1.42

bats

1.31

 Rays

1.31

waves

1.12

Ray

1.10

rises

1.07

sheets

1.05

Activations Density 0.010%

medical imaging related terms, specifically X-rays

references to X-rays and their implications in medical contexts

No Comments

No Known Activations