INDEX

Explanations

proper nouns related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of specific names and locations, particularly "Ventura" and "Venice."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ences

-0.78

yne

-0.74

 cakes

-0.71

udeb

-0.71

strap

-0.70

andr

-0.68

elson

-0.67

ird

-0.67

erred

-0.65

 partName

-0.64

POSITIVE LOGITS

 County

0.74

mission

0.73

boat

0.73

Interstitial

0.73

 Canal

0.72

 Ventura

0.72

jug

0.72

apeake

0.71

Benz

0.70

 Register

0.69

Activations Density 0.021%

proper nouns related to geographical locations

repeated mentions of specific names and locations, particularly "Ventura" and "Venice."

No Comments

No Known Activations