INDEX

Explanations

the word "not" in sentences

oai_token-act-pair · gpt-3.5-turbo

negations or phrases indicating something that is not the case

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

 Seasons

-0.78

 Citiz

-0.74

itiz

-0.73

 Opportun

-0.71

PDATE

-0.69

 Communities

-0.69

lined

-0.69

 Modes

-0.69

inventoryQuantity

-0.68

 Companies

-0.67

POSITIVE LOGITS

 necessarily

1.28

icably

1.11

 bother

1.06

 exist

1.04

 belong

0.98

 hesitate

0.97

necess

0.96

 preclude

0.95

 distinguish

0.94

 intend

0.93

Activations Density 0.132%

the word "not" in sentences

negations or phrases indicating something that is not the case

No Comments

No Known Activations