INDEX

Explanations

the personal pronoun "I."

oai_token-act-pair · gpt-3.5-turbo

the pronoun "I" and its associated phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 selves

-0.70

 adhesive

-0.69

 decoration

-0.67

 perfection

-0.65

 membrane

-0.63

 souls

-0.63

 substitutes

-0.62

 Violet

-0.61

ego

-0.59

 abdom

-0.59

POSITIVE LOGITS

'm

1.13

xtap

1.11

ANS

1.02

UC

1.01

ANA

1.00

WI

0.98

ERA

0.96

lan

0.95

've

0.94

deals

0.92

Activations Density 0.219%

the personal pronoun "I."

the pronoun "I" and its associated phrases

No Comments

No Known Activations