INDEX

Explanations

proper nouns related to various individuals and locations

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to specific individuals or entities, particularly their names or titles

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

Not in Any Lists

No Comments

Negative Logits

 recount

-0.67

 innocence

-0.67

Constructed

-0.64

 STATS

-0.64

Ou

-0.61

 quar

-0.59

 universes

-0.58

 succession

-0.58

 Buddy

-0.58

 attendant

-0.58

POSITIVE LOGITS

edo

1.12

oshenko

0.99

culosis

0.86

ttle

0.85

acco

0.85

obl

0.85

nel

0.83

anian

0.81

asury

0.81

bley

0.80

Activations Density 0.108%

proper nouns related to various individuals and locations

words or phrases related to specific individuals or entities, particularly their names or titles

No Comments

No Known Activations