INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific entities, brands, or organizations

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

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

abwe

-0.83

anchester

-0.74

sembly

-0.71

mble

-0.71

aphael

-0.69

assetsadobe

-0.68

 coerc

-0.67

 myster

-0.67

ccording

-0.67

 princ

-0.67

POSITIVE LOGITS

 Builder

0.62

 Labs

0.60

 Tower

0.58

 Sight

0.58

Streamer

0.57

 Creek

0.57

 Towers

0.57

 Passage

0.56

 Tears

0.56

 itself

0.55

Activations Density 0.464%

proper nouns

proper nouns related to specific entities, brands, or organizations

No Comments

No Known Activations