INDEX

Explanations

mentions of war-related terms or concepts

oai_token-act-pair · gpt-3.5-turbo

references to "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 @ 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

FORMATION

-0.88

Ħ¢

-0.83

essee

-0.82

aminer

-0.74

sembly

-0.74

ostics

-0.73

AUT

-0.70

Asset

-0.70

prints

-0.69

Distance

-0.68

POSITIVE LOGITS

fare

1.21

lords

1.14

riors

1.10

lord

1.08

rior

1.07

 waged

0.96

fighting

0.96

ring

0.94

fighter

0.90

fighters

0.82

Activations Density 0.030%

mentions of war-related terms or concepts

references to "war" in various contexts

No Comments

No Known Activations