INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the determiner "An" at varying levels of emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĸº

-0.85

EngineDebug

-0.81

BOOK

-0.77

BLE

-0.74

åĨ

-0.68

åĭ

-0.68

 pupils

-0.67

NESS

-0.66

MEN

-0.65

STEM

-0.65

POSITIVE LOGITS

omaly

1.21

alyses

1.20

onym

1.17

alys

1.15

notation

1.13

notations

1.13

alogue

1.10

omal

1.09

esthetic

1.07

xiety

1.06

Activations Density 0.054%

proper nouns

the determiner "An" at varying levels of emphasis

No Comments

No Known Activations