INDEX

Explanations

references to travel destinations within a specific organization

oai_token-act-pair · gpt-3.5-turbo

references to travel and exploration

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

avez

-0.66

eff

-0.62

oust

-0.61

adle

-0.60

 diamond

-0.60

cephal

-0.60

 linguistic

-0.59

 cherry

-0.59

 academ

-0.59

ear

-0.58

POSITIVE LOGITS

 Travels

1.24

NetMessage

0.81

 Flavoring

0.80

 destinations

0.78

è¦ļéĨĴ

0.77

 VIDEOS

0.74

ECTION

0.73

 Instruments

0.73

hip

0.72

dayName

0.72

Activations Density 0.013%

references to travel destinations within a specific organization

references to travel and exploration

No Comments

No Known Activations