INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to people, places, or organizations

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

................................

-0.73

probably

-0.71

©¶æ¥µ

-0.70

lime

-0.69

Sharp

-0.64

acceptable

-0.63

INC

-0.62

marked

-0.60

Spread

-0.59

POSITIVE LOGITS

 arrives

1.01

 enters

0.98

 finally

0.97

 arrived

0.96

 debuted

0.95

 reaches

0.87

 decides

0.87

 asked

0.86

 comes

0.86

 approached

0.85

Activations Density 0.292%

proper nouns

proper nouns related to people, places, or organizations

No Comments

No Known Activations