INDEX

Explanations

references to universities and academic institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 wikipagina

-0.79

WireFormatLite

-0.72

 Monfieur

-0.69

 Gabb

-0.67

 ujednoznacz

-0.67

+#+#

-0.67

 Ediciones

-0.67

GetBytes

-0.67

 reak

-0.67

ეთ

-0.66

POSITIVE LOGITS

 University

2.46

 university

2.25

University

2.18

university

2.12

 UNIVERSITY

1.97

 universities

1.86

 Universities

1.73

 Univ

1.71

UNIVERSITY

1.56

 universitarios

1.53

Activations Density 0.045%

references to universities and academic institutions

No Comments

No Known Activations