INDEX

Explanations

references to comparisons or distinctions among entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ValueStyle

-0.61

 tuturor

-0.59

 سكانية

-0.57

 greu

-0.57

dotenv

-0.53

kendo

-0.53

 vechi

-0.52

TagHelpers

-0.52

 viață

-0.51

 Référence

-0.50

POSITIVE LOGITS

roleum

0.63

Portail

0.62

就是

0.60

DoubleQuotes

0.60

 Ansprüche

0.59

providedIn

0.58

 else

0.56

Longrightarrow

0.55

toHave

0.55

itism

0.55

Activations Density 0.198%

references to comparisons or distinctions among entities

No Comments

No Known Activations