INDEX

Explanations

references to logos

oai_token-act-pair · gpt-3.5-turbo

references to logos and branding

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

hower

-0.77

hurst

-0.75

neau

-0.73

Ago

-0.69

kus

-0.67

Ã©n

-0.65

erve

-0.65

dose

-0.64

cible

-0.63

ieri

-0.63

POSITIVE LOGITS

 logos

1.05

plates

0.96

 logo

0.92

 Doodle

0.85

 trademarks

0.85

prints

0.83

 redesign

0.81

 Logo

0.81

 slogan

0.80

 colour

0.79

Activations Density 0.069%

references to logos

references to logos and branding

No Comments

No Known Activations