INDEX

Explanations

elements related to user interface components and functionalities

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

IsPostBack

-0.72

 propOrder

-0.69

invokeLater

-0.61

сылкі

-0.57

acterial

-0.55

 ***!

-0.55

 "..\..\

-0.55

Autoritní

-0.54

脚注の使い方

-0.52

POSITIVE LOGITS

 icon

0.76

 Icon

0.66

 symbol

0.64

 Symbols

0.63

 sumpay

0.63

 ICON

0.63

icon

0.62

 icons

0.62

енча

0.61

 SYMBOL

0.61

Activations Density 0.094%

elements related to user interface components and functionalities

No Comments

No Known Activations