INDEX

Explanations

words related to geographic locations or entities

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

findpost

-0.77

الإنجليزية

-0.70

 doInBackground

-0.65

ellschaft

-0.62

 שוליים

-0.62

expandindo

-0.59

+#+

-0.58

"/></

-0.57

 consultato

-0.57

ActionCreators

-0.56

POSITIVE LOGITS

ucid

0.51

 ddelweddau

0.44

﹍﹍﹍

0.44

 olev

0.44

újo

0.43

 consist

0.42

 entanto

0.42

XmlAccessType

0.42

osgi

0.41

cune

0.41

Activations Density 0.064%

words related to geographic locations or entities

No Comments

No Known Activations