INDEX

Explanations

classified information

oai_token-act-pair · gpt-3.5-turbo

references to classified information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Wave

-0.75

LV

-0.73

vous

-0.72

DAY

-0.67

=-=-=-=-

-0.65

 stead

-0.63

 Candle

-0.63

place

-0.63

 Bale

-0.62

BO

-0.61

POSITIVE LOGITS

 classified

1.00

 briefings

0.94

classified

0.93

 classify

0.83

 markings

0.79

CLASSIFIED

0.77

 newsp

0.75

gew

0.72

encies

0.72

 veter

0.72

Activations Density 0.010%

classified information

references to classified information

No Comments

No Known Activations