INDEX

Explanations

the word "Medicine" and related phrases

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "medicine" in various contexts

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

ibilities

-0.78

 sqor

-0.78

flag

-0.67

ities

-0.67

 Strongh

-0.67

utter

-0.66

 Podesta

-0.65

imsy

-0.63

âĢ¢âĢ¢âĢ¢âĢ¢

-0.63

Operation

-0.62

POSITIVE LOGITS

 medicine

0.93

istry

0.93

 practitioner

0.91

utics

0.83

utical

0.80

 dispens

0.77

 practitioners

0.76

 cures

0.75

 cabinets

0.75

iology

0.73

Activations Density 0.013%

the word "Medicine" and related phrases

mentions of the term "medicine" in various contexts

No Comments

No Known Activations