INDEX

Explanations

mentions of military-related terms or organizations, specifically variations of the term "Corps."

oai_token-act-pair · gpt-3.5-turbo

mentions of different "Corps" in various contexts

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

izer

-0.75

èª

-0.73

âĹ¼

-0.69

 productive

-0.68

MLG

-0.66

jad

-0.65

*/(

-0.64

izers

-0.63

 lucid

-0.63

 Icelandic

-0.62

POSITIVE LOGITS

naire

1.18

ombat

0.97

 Corps

0.94

hire

0.90

naires

0.89

enne

0.87

 Headquarters

0.87

chwitz

0.82

hip

0.81

xon

0.80

Activations Density 0.011%

mentions of military-related terms or organizations, specifically variations of the term "Corps."

mentions of different "Corps" in various contexts

No Comments

No Known Activations