INDEX

Explanations

instances of the word "set" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 contextLoads

-0.80

angkutan

-0.69

 виправивши

-0.67

 getTotal

-0.65

 getColor

-0.65

ędzynarod

-0.65

adni

-0.64

addHandler

-0.64

 AppColors

-0.63

fatter

-0.62

POSITIVE LOGITS

set

1.93

Set

1.73

SET

1.61

Set

1.58

 setting

1.55

set

1.51

 sets

1.46

 Setting

1.46

 SETTING

1.35

Setting

1.35

Activations Density 0.116%

instances of the word "set" and its variations in various contexts

No Comments

No Known Activations