INDEX

Explanations

negative or critical character descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

HandlerContext

-0.64

جستارهای

-0.64

ChromeDriver

-0.61

 defStyleAttr

-0.60

astify

-0.57

 useAuth

-0.57

TRIBUN

-0.55

enderror

-0.55

 useContext

-0.55

ngdoc

-0.53

POSITIVE LOGITS

 autorytatywna

0.68

InputBorder

0.67

 wast

0.61

 roue

0.60

tagHelperRunner

0.57

ณ์

0.57

 raff

0.55

WAS

0.55

 wheeler

0.54

 cant

0.54

Activations Density 0.377%

negative or critical character descriptions

No Comments

No Known Activations

negative or critical character descriptions

No Comments

No Known Activations