INDEX

Explanations

terms related to the historical period known as the Cold War

oai_token-act-pair · gpt-3.5-turbo

references to the Cold War

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iage

-0.92

eca

-0.85

Companies

-0.82

enance

-0.75

alties

-0.72

ioned

-0.71

semb

-0.70

umper

-0.69

ADRA

-0.68

edIn

-0.68

POSITIVE LOGITS

 Cold

0.86

 winters

0.76

ocaust

0.73

 fusion

0.72

 warmer

0.72

robe

0.72

idge

0.71

 buildup

0.70

 colder

0.67

cold

0.67

Activations Density 0.007%

terms related to the historical period known as the Cold War

references to the Cold War

No Comments

No Known Activations