INDEX

Explanations

mentions of studies, their inclusion criteria, and data summarization methods

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

listing quantities and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

bein

-0.38

OSSARY

-0.37

期刊论文

-0.36

styleable

-0.35

 Velocity

-0.33

haften

-0.33

章节错误

-0.33

executeQuery

-0.32

bau

-0.32

 Domains

-0.32

POSITIVE LOGITS

Diweddarwch

0.53

 للاسماء

0.52

yyr

0.47

jenost

0.47

gjenge

0.46

醐

0.46

 مرئيه

0.46

rrggbb

0.45

 оригіналу

0.45

RTEX

0.44

Activations Density 0.121%

mentions of studies, their inclusion criteria, and data summarization methods

listing quantities and items

No Comments

No Known Activations