INDEX

Explanations

words related to European locations or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Eur" and related variations thereof

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

erry

-0.79

mie

-0.78

arians

-0.76

etti

-0.75

arro

-0.75

arian

-0.74

ez

-0.72

olk

-0.72

lain

-0.71

aran

-0.71

POSITIVE LOGITS

htaking

0.80

teenth

0.73

 livest

0.68

 deceive

0.67

minent

0.65

judicial

0.64

 Juda

0.64

pse

0.64

choes

0.64

 adultery

0.62

Activations Density 0.020%

words related to European locations or entities

occurrences of the term "Eur" and related variations thereof

No Known Activations