INDEX

Explanations

mentions of banners

oai_token-act-pair · gpt-3.5-turbo

references to banners in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

urrency

-0.76

ulu

-0.72

cephal

-0.72

OTOS

-0.69

AE

-0.68

itals

-0.67

nesota

-0.67

elsen

-0.65

yon

-0.65

olated

-0.65

POSITIVE LOGITS

 banners

1.03

 banner

1.01

pole

0.99

boards

0.84

strip

0.83

 proclaiming

0.82

board

0.81

holder

0.77

ram

0.75

 slogan

0.72

Activations Density 0.023%

mentions of banners

references to banners in various contexts

No Comments

No Known Activations