INDEX

Explanations

calls to action and encouragement for feedback or engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

me

-0.98

 conmigo

-0.84

僕は

-0.82

自分は

-0.77

 comigo

-0.76

わたしは

-0.75

僕も

-0.70

私は

-0.68

yourself

-0.68

自分も

-0.67

POSITIVE LOGITS

you

1.39

 vocês

1.09

 ustedes

0.98

you

0.95

 você

0.86

You

0.82

YOU

0.75

 vosotros

0.73

You

0.73

 thee

0.73

Activations Density 0.300%

calls to action and encouragement for feedback or engagement

No Comments

No Known Activations