INDEX

Explanations

phrases related to numerical values or rankings

oai_token-act-pair · gpt-3.5-turbo

references to the numbers six, five, and four, particularly in a context related to sports or competition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

USD

-0.72

 crawl

-0.69

OCK

-0.68

igation

-0.67

adel

-0.63

è¦ļéĨĴ

-0.62

 clock

-0.61

 includ

-0.61

DOI

-0.61

cd

-0.61

POSITIVE LOGITS

teen

1.43

een

1.05

teenth

0.95

 Hundred

0.92

 Lives

0.92

 Mile

0.91

 Thousand

0.86

 Hour

0.85

 Seasons

0.83

 Vision

0.82

Activations Density 0.053%

phrases related to numerical values or rankings

references to the numbers six, five, and four, particularly in a context related to sports or competition

No Comments

No Known Activations