INDEX

Explanations

phrases related to forgetting or neglecting to take action

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

 estimés

-0.77

 snippetHide

-0.73

Personendaten

-0.68

Bioaccumulative

-0.67

]^{-

-0.66

acke

-0.66

argest

-0.66

,:),

-0.66

 BoxFit

-0.65

 cherchés

-0.65

POSITIVE LOGITS

 forgot

0.83

 reminder

0.75

 remember

0.71

forgot

0.68

 remind

0.68

 Remember

0.67

Remember

0.67

 remembering

0.67

 Forgot

0.67

 reminding

0.64

Activations Density 0.286%

phrases related to forgetting or neglecting to take action

No Comments

No Known Activations