INDEX

Explanations

references to specific airlines

oai_token-act-pair · gpt-3.5-turbo

mentions of airline companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

âĶĢâĶĢ

-0.80

liest

-0.77

 Schne

-0.67

SPONSORED

-0.66

obj

-0.66

Jah

-0.64

 motions

-0.64

arist

-0.63

ebook

-0.62

nered

-0.62

POSITIVE LOGITS

 Airlines

1.16

 Plaza

0.90

ports

0.85

otive

0.84

 Holdings

0.83

 Airways

0.82

 Lounge

0.81

Pass

0.80

daq

0.80

 Stores

0.77

Activations Density 0.022%

references to specific airlines

mentions of airline companies

No Comments

No Known Activations