INDEX

Explanations

mentions of internships or programs involving internships

oai_token-act-pair · gpt-3.5-turbo

mentions of internships and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 è£ıè¦ļéĨĴ

-0.67

 bluff

-0.66

 signalling

-0.62

âĢ¢âĢ¢

-0.62

 Caucasus

-0.60

 palms

-0.59

 transmitting

-0.59

lower

-0.58

 ACTION

-0.58

IRO

-0.57

POSITIVE LOGITS

ships

1.72

ationally

1.32

ship

1.24

als

1.06

ment

1.00

ational

1.00

elong

0.95

ials

0.95

ation

0.94

auts

0.93

Activations Density 0.040%

mentions of internships or programs involving internships

mentions of internships and related terms

No Comments

No Known Activations