INDEX

Explanations

terms related to North Korean leader Kim Jong-un

oai_token-act-pair · gpt-3.5-turbo

references to Kim Jong-un and related political dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

AVG

-0.73

 REAL

-0.69

 subscriber

-0.67

 defin

-0.67

 Digest

-0.66

 EntityItem

-0.63

McA

-0.62

 digest

-0.61

 msec

-0.60

 goat

-0.59

POSITIVE LOGITS

sung

1.36

Hong

1.14

jin

1.12

Tai

1.10

Yang

1.10

wei

1.09

Han

1.09

jong

1.07

Shin

1.07

Yan

1.04

Activations Density 0.022%

terms related to North Korean leader Kim Jong-un

references to Kim Jong-un and related political dynamics

No Comments

No Known Activations