INDEX

Explanations

attributes related to logical assertions within data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 يتيمه

-0.74

tagHelperRunner

-0.64

Portail

-0.62

 Fond

-0.61

Fond

-0.58

 estekak

-0.58

lī

-0.57

Portale

-0.55

 financiera

-0.55

 financière

-0.55

POSITIVE LOGITS

“……

0.67

webElement

0.63

 CURLOPT

0.59

jws

0.58

+][

0.56

……"

0.55

queryInterface

0.51

сшта

0.50

<>("

0.50

↵↵↵

0.50

Activations Density 0.258%

attributes related to logical assertions within data structures

No Comments

No Known Activations