INDEX

Explanations

phrases mentioning specific geographic locations, especially with the word "Greater"

oai_token-act-pair · gpt-3.5-turbo

references to geographical regions and areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ulating

-0.90

ulators

-0.89

ulates

-0.85

sters

-0.83

ulation

-0.82

ulated

-0.82

ulations

-0.81

tops

-0.81

ulator

-0.81

tics

-0.77

POSITIVE LOGITS

 Territories

0.95

 Greater

0.85

 Than

0.80

 States

0.77

 Leban

0.75

 Albania

0.75

 Equal

0.74

 Regional

0.74

 Utilities

0.73

 Tire

0.73

Activations Density 0.032%

phrases mentioning specific geographic locations, especially with the word "Greater"

references to geographical regions and areas

No Comments

No Known Activations