INDEX

Explanations

proper nouns or names of people, places, or organizations

oai_token-act-pair · gpt-3.5-turbo

names of people, places, or organizations that are significant in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 thereto

-0.82

 thereof

-0.78

])

-0.67

Ħ¢

-0.65

 ..."

-0.64

 âĢ¦"

-0.63

 respectively

-0.63

 guiIcon

-0.63

Î¿

-0.61

 trans

-0.61

POSITIVE LOGITS

jamin

1.02

xiety

1.02

odore

0.99

resa

0.96

anyahu

0.92

withstanding

0.91

ifax

0.90

nsic

0.89

lahoma

0.87

alyst

0.87

Activations Density 0.423%

proper nouns or names of people, places, or organizations

names of people, places, or organizations that are significant in context

No Comments

No Known Activations