INDEX

Explanations

references to academic or professional fields of study

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

fields of study or professions

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

 transpar

-0.51

polic

-0.50

商品説明

-0.50

warted

-0.49

 MNRAS

-0.46

ration

-0.46

intios

-0.46

Vaya

-0.45

Clik

-0.45

 kask

-0.45

POSITIVE LOGITS

 field

0.60

 bidang

0.56

 profession

0.55

 professions

0.54

 careers

0.54

 especializado

0.53

领域

0.51

 career

0.50

 campo

0.50

分野

0.50

Activations Density 0.012%

references to academic or professional fields of study

fields of study or professions

No Comments

No Known Activations