INDEX

Explanations

phrases emphasizing importance or significance

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "just."

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

 seiz

-0.76

undai

-0.73

 fuse

-0.73

 necks

-0.73

antis

-0.67

yip

-0.67

 destro

-0.67

insula

-0.65

leneck

-0.63

ixel

-0.63

POSITIVE LOGITS

ifiable

1.32

ifications

1.01

IFIED

0.96

 kidding

0.95

 plain

0.90

ified

0.84

if

0.83

itia

0.76

 gonna

0.75

ices

0.74

Activations Density 0.048%

phrases emphasizing importance or significance

the repetition of the word "just."

No Comments

No Known Activations