INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

key phrases related to status, condition, or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Container

-0.67

AMA

-0.61

 Babel

-0.61

ramid

-0.58

 Slate

-0.58

 pulp

-0.56

 Corm

-0.56

andise

-0.56

Bomb

-0.55

 constitu

-0.55

POSITIVE LOGITS

ises

0.72

 prosec

0.71

icable

0.71

ÑĤ

0.69

izes

0.69

imeo

0.69

^{

0.68

itiz

0.68

ä¸

0.68

pired

0.67

Activations Density 0.561%

words related to geographical locations

key phrases related to status, condition, or location

No Comments

No Known Activations