INDEX

Explanations

information related to gaming abilities and effects

oai_token-act-pair · gpt-3.5-turbo

terms related to damage, effects, and mechanics in a gaming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Redd

-0.83

ovie

-0.82

Reviewer

-0.81

çĶ°

-0.80

 Homo

-0.80

jl

-0.70

 Reich

-0.69

wed

-0.68

ð

-0.68

 Azerb

-0.68

POSITIVE LOGITS

 cooldown

1.25

 Cooldown

1.13

dmg

1.00

 Damage

1.00

 projectiles

1.00

damage

1.00

AoE

0.99

Damage

0.99

nergy

0.97

oldown

0.97

Activations Density 0.126%

information related to gaming abilities and effects

terms related to damage, effects, and mechanics in a gaming context

No Comments

No Known Activations