INDEX

Explanations

references to stories in various contexts, such as radio shows, television programs, news articles, and books

oai_token-act-pair · gpt-3.5-turbo

references to different types of stories and narrative content

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Ķ

-0.80

çĦ

-0.75

×ŀ

-0.70

livion

-0.68

arb

-0.67

 forestry

-0.66

 labor

-0.65

 protective

-0.65

×Ķ

-0.64

ously

-0.62

POSITIVE LOGITS

 Tests

1.08

 Rooms

1.08

 Advice

1.07

 Languages

1.06

 Shots

1.05

 Affect

1.03

 Programs

1.03

 Costs

1.02

 Scores

1.01

 Matters

1.01

Activations Density 0.127%

references to stories in various contexts, such as radio shows, television programs, news articles, and books

references to different types of stories and narrative content

No Known Activations