INDEX

Explanations

locations and specific places

oai_token-act-pair · gpt-3.5-turbo

names of geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

surface

-0.76

quo

-0.62

inventoryQuantity

-0.61

 Rebell

-0.60

emonic

-0.60

sbm

-0.59

channelAvailability

-0.58

adder

-0.58

ibaba

-0.57

gamer

-0.56

POSITIVE LOGITS

TX

1.11

 Pennsylvania

1.02

 Ontario

1.01

NJ

1.01

 Illinois

1.01

 Calif

0.99

 Ohio

0.99

NY

0.99

 Maryland

0.98

 California

0.96

Activations Density 0.183%

locations and specific places

names of geographic locations

No Comments

No Known Activations