INDEX

Explanations

mentions of universities and academic institutions

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

names of universities

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

UnusedPrivate

-0.61

Diweddarwch

-0.60

 nahilalakip

-0.58

 disambiguazione

-0.57

 ujednoznacz

-0.53

ValueGeneration

-0.53

 мәкал

-0.51

 OMITBAD

-0.50

 NgModule

-0.49

imageshack

-0.49

POSITIVE LOGITS

 University

0.66

 university

0.63

NYU

0.58

 Stanford

0.57

 Princeton

0.56

 Columbia

0.52

 College

0.50

 Harvard

0.50

 professor

0.49

 ſch

0.49

Activations Density 0.031%

mentions of universities and academic institutions

names of universities

No Comments

No Known Activations