INDEX

Explanations

words related to cards and playing cards in a strategic card game context

oai_token-act-pair · gpt-3.5-turbo

topics related to deck-building in card games

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

SIG

-0.74

HIP

-0.73

 Satellite

-0.68

 Gaul

-0.68

 Payments

-0.66

 Thames

-0.66

 IPCC

-0.66

 Geneva

-0.66

 commencement

-0.66

phrine

-0.65

POSITIVE LOGITS

lists

1.19

builder

1.10

list

0.91

arios

0.89

 deck

0.88

 decks

0.87

ery

0.86

eries

0.85

 archetype

0.84

sheet

0.83

Activations Density 0.022%

words related to cards and playing cards in a strategic card game context

topics related to deck-building in card games

No Comments

No Known Activations