INDEX

Explanations

terms related to specific phrases or names like "Credit Farming," "Slender Billy," and "Google Effect."

oai_token-act-pair · gpt-3.5-turbo

specific names or titles related to entertainment and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.79

fitted

-0.67

ometimes

-0.61

 respectively

-0.60

upon

-0.59

uitive

-0.59

surprisingly

-0.58

trak

-0.58

 strutConnector

-0.56

prisingly

-0.56

POSITIVE LOGITS

").

1.74

")

1.73

"]

1.66

"),

1.63

"?

1.63

",

1.60

"—

1.53

".

1.51

1.47

"!

1.46

Activations Density 0.555%

terms related to specific phrases or names like "Credit Farming," "Slender Billy," and "Google Effect."

specific names or titles related to entertainment and media

No Comments

No Known Activations