INDEX

Explanations

phrases and names related to political figures and organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly politicians, and their associated contexts

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

kered

-0.83

uracy

-0.77

 Petersburg

-0.75

laus

-0.75

umber

-0.70

esville

-0.70

nis

-0.69

oreal

-0.69

avid

-0.67

central

-0.65

POSITIVE LOGITS

wcs

0.86

 Booker

0.76

 Buffett

0.74

âĸ¬

0.69

cci

0.68

Vie

0.65

 Prize

0.65

llo

0.64

Tau

0.62

ogue

0.60

Activations Density 0.036%

phrases and names related to political figures and organizations

mentions of specific individuals, particularly politicians, and their associated contexts

No Comments

No Known Activations