INDEX

Explanations

proper nouns or names, potentially related to individuals or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people, places, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĶĢâĶĢ

-0.70

 lowly

-0.67

 stoked

-0.65

 heck

-0.65

recorded

-0.61

é¾įå¥ĳå£«

-0.60

theless

-0.60

yip

-0.60

POSE

-0.59

 bottleneck

-0.59

POSITIVE LOGITS

eworks

1.00

itaire

0.80

Maker

0.76

naire

0.76

Ltd

0.75

ienne

0.75

 Resort

0.71

enstein

0.70

anca

0.70

iatures

0.68

Activations Density 0.401%

proper nouns or names, potentially related to individuals or locations

proper nouns, particularly names of people, places, and organizations

No Comments

No Known Activations