INDEX

Explanations

keywords related to a specific type of card game involving strategy and gameplay elements

oai_token-act-pair · gpt-3.5-turbo

elements associated with card games and gameplay mechanics

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

IFrame

Link

Negative Logits

HIP

-0.93

 Philips

-0.74

Fit

-0.71

 accredited

-0.70

Hue

-0.69

 Engels

-0.67

 Rodrig

-0.66

 commencement

-0.66

 Mens

-0.66

ESA

-0.66

POSITIVE LOGITS

 mana

1.03

 decks

0.99

 cards

0.97

magic

0.93

 Spells

0.92

Spell

0.90

caster

0.90

 Spell

0.86

 spell

0.84

 orcs

0.83

Activations Density 0.163%

keywords related to a specific type of card game involving strategy and gameplay elements

elements associated with card games and gameplay mechanics

No Known Activations