INDEX

Explanations

words related to conflicts and wars

oai_token-act-pair · gpt-3.5-turbo

references to war and related conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

essee

-0.76

aminer

-0.75

gow

-0.73

sembly

-0.72

 Universe

-0.71

obook

-0.71

Asset

-0.70

FORMATION

-0.70

 Incarnation

-0.67

ostics

-0.66

POSITIVE LOGITS

fare

1.24

lords

1.19

lord

1.18

riors

1.10

rior

1.07

fighting

1.00

 waged

1.00

fighter

0.99

ring

0.92

fighters

0.89

Activations Density 0.037%

words related to conflicts and wars

references to war and related conflicts

No Comments

No Known Activations