INDEX

Explanations

instances of user engagement or inquiries for information

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

diverse language words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 brief

-0.45

 mini

-0.44

 Mini

-0.43

 summary

-0.43

 Summary

-0.41

 Brief

-0.38

 spot

-0.36

 sounds

-0.36

mini

-0.36

 short

-0.35

POSITIVE LOGITS

 Administrativna

0.77

 мәкал

0.77

Personendaten

0.70

 Italijanski

0.64

 kaarangay

0.64

脚注の使い方

0.63

 Савезне

0.63

 оригіналу

0.62

 تضيفلها

0.62

----</

0.61

Activations Density 0.000%

instances of user engagement or inquiries for information

diverse language words

No Comments

No Known Activations