INDEX

Explanations

proper nouns and specific terms related to various domains, such as medical products, locations, and individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of places or entities

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

 animated

-0.69

 joking

-0.68

 literal

-0.68

 ______

-0.67

 hilarious

-0.66

 commentary

-0.64

 humor

-0.63

 puzzle

-0.63

...]

-0.63

 foreground

-0.63

POSITIVE LOGITS

Health

0.95

Corp

0.94

Care

0.93

Bank

0.91

 Services

0.90

Pay

0.90

Point

0.90

 Foods

0.88

Services

0.88

City

0.86

Activations Density 0.415%

proper nouns and specific terms related to various domains, such as medical products, locations, and individuals

proper nouns and names of places or entities

No Comments

No Known Activations