INDEX

Explanations

words that contain the letters "ri" consecutively

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the substring "ri."

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

é¾

-0.82

enegger

-0.73

manship

-0.71

 Pengu

-0.70

lot

-0.68

 chips

-0.67

 Brunswick

-0.67

CPC

-0.67

milo

-0.67

 Izan

-0.66

POSITIVE LOGITS

ving

1.18

quez

1.12

vals

1.10

zzle

1.05

quet

1.02

jen

0.99

ja

0.98

jah

0.97

zona

0.97

pper

0.97

Activations Density 0.022%

words that contain the letters "ri" consecutively

repeated instances of the substring "ri."

No Comments

No Known Activations