INDEX

Explanations

instances of the word "show" and its variations, indicating a focus on demonstrating or presenting information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 lèvres

-0.83

 Brito

-0.71

Spacing

-0.67

 brazos

-0.66

zünd

-0.66

 Balt

-0.64

 plazos

-0.63

 esenciales

-0.63

zupeł

-0.62

 palavra

-0.62

POSITIVE LOGITS

 Showing

1.53

 SHOWING

1.52

 Shows

1.48

Showing

1.45

 showing

1.44

Shows

1.42

 shows

1.41

shows

1.40

showing

1.38

 shown

1.37

Activations Density 0.173%

instances of the word "show" and its variations, indicating a focus on demonstrating or presenting information

No Comments

No Known Activations