INDEX

Explanations

references to television series and their relationships to the creators, particularly focusing on connections between iconic shows and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 film

-0.57

 movie

-0.50

 eloku

-0.45

ForRow

-0.44

 films

-0.42

ito

-0.41

eca

-0.40

Filmography

-0.40

film

-0.39

滕

-0.38

POSITIVE LOGITS



0.72

 חיצוניים

0.69

Efq

0.69

ſelf

0.66

 iſt

0.66

脚注の使い方

0.65

reszcie

0.65

principalTable

0.64

 Houſe

0.64

cidae

0.64

Activations Density 0.096%

references to television series and their relationships to the creators, particularly focusing on connections between iconic shows and characters

No Comments

No Known Activations