INDEX

Explanations

phrases and context related to personal experiences and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 defaultstate

-0.81

PhysRevD

-0.67

Slf

-0.60

topt

-0.56

 newBuilder

-0.55

出版年

-0.55

AxisAlignment

-0.54

 հղումներ

-0.53

ح

-0.52

mockMvc

-0.52

POSITIVE LOGITS

 previous

0.84

 предыду

0.81

 früheren

0.73

 previously

0.72

 traditionally

0.71

 earlier

0.71

previous

0.70

 Previous

0.70

Previous

0.68

 PREVIOUS

0.68

Activations Density 0.684%

phrases and context related to personal experiences and preferences

No Comments

No Known Activations