INDEX

Explanations

references to Donald Trump

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ंदीखरीदारी

-0.69



-0.64

PreExecute

-0.64

 Seeder

-0.61

/*---

-0.60

VIAF

-0.60

 direct

-0.56

tonode

-0.54

तान

-0.54

uche

-0.53

POSITIVE LOGITS

FontOfSize

0.62

 fight

0.61

 Trump

0.61

 betweenstory

0.57

 PARSER

0.56

 Russell

0.56

ışık

0.55

 russell

0.55

fight

0.54

jeka

0.54

Activations Density 0.085%

references to Donald Trump

No Comments

No Known Activations