INDEX

Explanations

locations or regions with the word "Greater" in their names

oai_token-act-pair · gpt-3.5-turbo

mentions of geographic regions or areas

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

tops

-0.87

ulators

-0.85

TED

-0.82

ulating

-0.81

ulates

-0.80

pta

-0.80

ulator

-0.76

ulated

-0.75

breaks

-0.74

dates

-0.74

POSITIVE LOGITS

 Greater

1.03

 eleph

0.91

 Than

0.81

 guiIcon

0.78

 than

0.76

izont

0.75

 Equal

0.72

 Faster

0.71

 ende

0.70

 subsequ

0.68

Activations Density 0.005%

locations or regions with the word "Greater" in their names

mentions of geographic regions or areas

No Comments

No Known Activations