INDEX

Explanations

references to additional content, levels, maps, characters, and gameplay features in video games

oai_token-act-pair · gpt-3.5-turbo

references to new features or content in games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Wikipedia

-0.83

Virgin

-0.79

Georg

-0.76

govtrack

-0.75

ertodd

-0.75

çĶ°

-0.75

debian

-0.75

Krist

-0.74

ittee

-0.73

rists

-0.72

POSITIVE LOGITS

 quests

1.35

 dungeons

1.35

 playable

1.30

 missions

1.25

 enemies

1.24

 bosses

1.23

 endings

1.20

 gameplay

1.20

 costumes

1.18

 puzzles

1.17

Activations Density 0.321%

references to additional content, levels, maps, characters, and gameplay features in video games

references to new features or content in games

No Comments

No Known Activations