INDEX

Explanations

locations or countries

oai_token-act-pair · gpt-3.5-turbo

references to specific countries and locations

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

-0.77

Afee

-0.70

anza

-0.69

bats

-0.68

gotten

-0.67

igan

-0.66

 justices

-0.64

Boo

-0.63

¼

-0.63

bread

-0.62

POSITIVE LOGITS

 Territory

0.85

;;;;;;;;;;;;

0.82

 attm

0.74

 Converted

0.71

 Jung

0.70

 Feder

0.69

 Saud

0.68

 Dept

0.68

 respectively

0.68

 CrossRef

0.64

Activations Density 0.059%

locations or countries

references to specific countries and locations

No Comments

No Known Activations