INDEX

Explanations

cities and locations

oai_token-act-pair · gpt-3.5-turbo

city names and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

•single token firings

Individually fires on " Fresno", "Portland", "Denver", "ancouver", "Houston", "Atlanta", ..." Janeiro", ...etc

No Comments

Negative Logits

vana

-0.81

renheit

-0.72

ilater

-0.72

ãĤ½

-0.69

schild

-0.67

 recip

-0.67

Enlarge

-0.64

arial

-0.63

ãĥł

-0.63

VALUE

-0.62

POSITIVE LOGITS

 City

0.78

Zoo

0.78

 skyline

0.77

 Region

0.76

 resident

0.73

 Township

0.71

 Rapids

0.69

FC

0.68

 Transit

0.67

 Heights

0.67

Activations Density 0.231%

cities and locations

city names and geographic locations

No Comments

No Known Activations