INDEX

Explanations

terms related to assistance and support in various contexts

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

as well as

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Numerade

-0.69

Билгалдахарш

-0.65

replyreport

-0.59

Autoritní

-0.59

RTLD

-0.57

 autorytatywna

-0.57

 Verſ

-0.54

 EconPapers

-0.54

 otomatig

-0.53

adaptiveStyles

-0.52

POSITIVE LOGITS

sowie

0.42

0.34

 numerous

0.33

 sekä

0.32

 serta

0.32

 varandra

0.31

 nonché

0.30

 وكذلك

0.30

 Grüsse

0.30

gehende

0.29

Activations Density 0.048%

terms related to assistance and support in various contexts

as well as

No Comments

No Known Activations