INDEX

Explanations

text related to the significance of a specific aspect in various contexts or scenarios

oai_token-act-pair · gpt-3.5-turbo

articles indicating significant roles 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 subordinates

-0.69

oons

-0.67

 Emails

-0.66

Edit

-0.66

coins

-0.65

 docs

-0.65

iffs

-0.63

 curls

-0.63

evidence

-0.63

 edits

-0.62

POSITIVE LOGITS

lot

1.28

 plethora

1.16

 whopping

1.09

 considerable

1.08

 variety

1.02

 relatively

1.01

 tremendous

1.01

 multitude

1.00

 significant

0.98

 hefty

0.98

Activations Density 0.461%

text related to the significance of a specific aspect in various contexts or scenarios

articles indicating significant roles in various contexts

No Comments

No Known Activations