INDEX

Explanations

proper nouns or titles

oai_token-act-pair · gpt-3.5-turbo

references to specific movies and entertainment franchises

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

etheless

-0.75

upon

-0.59

surprisingly

-0.55

ometimes

-0.55

ength

-0.54

 ãĢĮ

-0.54

uitive

-0.53

BILITIES

-0.52

bably

-0.52

uploads

-0.51

POSITIVE LOGITS

")

1.61

").

1.58

",

1.55

"),

1.54

"]

1.52

"—

1.49

1.47

"?

1.42

.")

1.41

".

1.41

Activations Density 0.456%

proper nouns or titles

references to specific movies and entertainment franchises

No Comments

No Known Activations