INDEX

Explanations

mentions of "inn"

oai_token-act-pair · gpt-3.5-turbo

references to hospitality-related establishments or accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

————————————————

-0.76

################################

-0.76

uyomi

-0.72

 Flavoring

-0.72

vich

-0.71

chell

-0.68

 Marijuana

-0.68

;;;;;;;;

-0.67

################

-0.67

UNCH

-0.66

POSITIVE LOGITS

inn

0.99

cloth

0.94

 tremend

0.84

 neighb

0.83

urst

0.81

ately

0.78

sword

0.77

ivery

0.76

ards

0.76

ipeg

0.75

Activations Density 0.009%

mentions of "inn"

references to hospitality-related establishments or accommodations

No Comments

No Known Activations