INDEX

Explanations

proper nouns related to geographical locations and names of organizations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enegger

-0.76

etheless

-0.69

cffff

-0.69

ãĤ¤ãĥĪ

-0.62

 cleaners

-0.61

 compr

-0.61

 womb

-0.59

 cage

-0.56

.).

-0.56

 lifestyle

-0.55

POSITIVE LOGITS

NET

0.72

inia

0.70

gate

0.67

ileaks

0.66

ety

0.65

pal

0.65

amon

0.64

land

0.64

ton

0.62

VA

0.62

Activations Density 0.532%

proper nouns related to geographical locations and names of organizations

No Comments

No Known Activations

proper nouns related to geographical locations and names of organizations

No Comments

No Known Activations