INDEX

Explanations

terms related to locations or organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific brands and institutions, particularly related to Starbucks and embassies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nered

-0.96

eric

-0.94

ship

-0.86

eer

-0.85

ships

-0.84

er

-0.83

ezvous

-0.81

Ł

-0.80

gling

-0.78

nd

-0.78

POSITIVE LOGITS

oup

0.65

Ame

0.65

BILITY

0.64

udeau

0.63

 Prot

0.63

itect

0.62

uthor

0.61

BIL

0.61

 Chal

0.61

oler

0.60

Activations Density 0.238%

terms related to locations or organizations

references to specific brands and institutions, particularly related to Starbucks and embassies

No Comments

No Known Activations