INDEX

Explanations

references or citations within a text

oai_token-act-pair · gpt-3.5-turbo

references to news agencies and media outlets

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

stood

-0.83

 beds

-0.67

ulously

-0.67

rous

-0.66

netflix

-0.66

hall

-0.66

gone

-0.65

isSpecialOrderable

-0.65

houses

-0.63

worldly

-0.62

POSITIVE LOGITS

 IMAGES

0.85

 Shutterstock

0.83

EVA

0.81

 Images

0.78

imedia

0.77

 Tribune

0.77

utterstock

0.75

 Photographer

0.75

verett

0.73

 Photo

0.72

Activations Density 0.092%

references or citations within a text

references to news agencies and media outlets

No Comments

No Known Activations