INDEX

Explanations

phrases related to education and academic achievements

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

education and degrees

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

tagHelperRunner

-0.60

GEBURTSDATUM

-0.59

Хьажоргаш

-0.57

 propOrder

-0.54

 kaarangay

-0.54

prefixer

-0.54

 للاسماء

-0.54

 चीज़ों

-0.53

ніципалі

-0.53

 occaf

-0.52

POSITIVE LOGITS

 obtained

0.74

 graduated

0.68

obtained

0.64

 received

0.60

 completed

0.60

 obtaining

0.59

 obtain

0.57

 attended

0.56

 uzyska

0.54

 obtuvo

0.54

Activations Density 0.013%

phrases related to education and academic achievements

education and degrees

No Comments

No Known Activations