INDEX

Explanations

phrases related to wars or conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "War" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sembly

-0.95

essee

-0.91

Ħ¢

-0.87

aunder

-0.82

İĭ

-0.81

ħĭ

-0.78

FORMATION

-0.74

etsk

-0.74

aminer

-0.72

ibilities

-0.67

POSITIVE LOGITS

fare

1.23

lords

1.23

rior

1.22

lord

1.16

riors

1.15

locks

0.94

war

0.87

ring

0.87

restling

0.86

ped

0.86

Activations Density 0.025%

phrases related to wars or conflicts

mentions of the word "War" in various contexts

No Comments

No Known Activations