INDEX

Explanations

names or terms related to locations

oai_token-act-pair · gpt-3.5-turbo

names or terms associated with specific places or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

llah

-0.73

OPLE

-0.71

=-=-

-0.68

 conscience

-0.67

ãģ®éŃĶ

-0.62

 INCLUD

-0.62

 Archdemon

-0.61

FAM

-0.61

 trope

-0.60

 loud

-0.60

POSITIVE LOGITS

heed

1.06

ttle

0.90

vel

0.90

emon

0.81

uania

0.80

ativity

0.79

ounge

0.78

aptop

0.78

warm

0.78

eport

0.78

Activations Density 0.085%

names or terms related to locations

names or terms associated with specific places or people

No Comments

No Known Activations