INDEX

Explanations

references to research studies and their goals

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

questioning or investigation

np_acts-logits-general · gemini-2.0-flash

seeking to determine whether

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

EnableWeb

-0.73

 SafeMath

-0.59

setVerticalGroup

-0.56

oredCriteria

-0.53

锆

-0.52

 perfectamente

-0.52

.(*

-0.51

nocache

-0.50

WebControls

-0.50

fredo

-0.50

POSITIVE LOGITS

 whether

1.00

whether

0.89

 Whether

0.86

Whether

0.82

 apakah

0.76

 determine

0.74

 האם

0.72

 WHETHER

0.72

是否有

0.71

how

0.70

Activations Density 0.630%

references to research studies and their goals

questioning or investigation

seeking to determine whether

No Comments

No Known Activations