INDEX

Explanations

words related to uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NamedQueries

-0.57

ագրություններ

-0.53

 innamor

-0.50

knex

-0.50

">'.$

-0.50

 mobilisation

-0.50

 debout

-0.49

 mobilization

-0.48

displayquote

-0.47

 yolks

-0.47

POSITIVE LOGITS

 supposedly

0.81

 apparente

0.75

 purported

0.75

 supposed

0.74

supposed

0.73

󠁢

0.72

EDEFAULT

0.71

edly

0.70

 pretended

0.70

 angeb

0.70

Activations Density 0.435%

words related to uncertainty or doubt

No Comments

No Known Activations