INDEX

Explanations

numerical values related to the quantity of one million

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of "million."

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

anooga

-0.78

displayText

-0.77

swick

-0.75

anwhile

-0.72

icipated

-0.70

krit

-0.67

ivalry

-0.67

ivism

-0.65

ivity

-0.65

ibrary

-0.65

POSITIVE LOGITS

aire

1.03

aires

0.99

 dollars

0.86

 dollar

0.80

dollar

0.79

ãĥĩãĤ£

0.75

 hectares

0.73

 Oaks

0.73

 watts

0.72

 miles

0.72

Activations Density 0.045%

numerical values related to the quantity of one million

phrases related to the concept of "million."

No Comments

No Known Activations