INDEX

Explanations

proper nouns related to people and places

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns and names related to people and entities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•L9 resid features following 'and'

No Comments

Negative Logits

and

-0.66

AND

-0.63

 indo

-0.62

 Learns

-0.60

 whereas

-0.59

".

-0.58

et

-0.57

 rather

-0.55

!".

-0.54

''.

-0.54

POSITIVE LOGITS

 alike

1.11

are

0.82

axter

0.79

oliath

0.75

 aren

0.73

 thereof

0.71

 were

0.70

 agree

0.70

 cohorts

0.68

ossal

0.65

Activations Density 0.653%

proper nouns related to people and places

specific proper nouns and names related to people and entities in various contexts

No Comments

No Known Activations