INDEX

Explanations

references to specific titles and notable figures in academic or ideological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Myron

-0.55

 Kenji

-0.50

adaptiveStyles

-0.49

IMPORTED

-0.49

 Magi

-0.45

 Whigs

-0.45

 Credo

-0.45

 Institutes

-0.44

AutoresizingMask

-0.44

 Kaya

-0.43

POSITIVE LOGITS

 للمعارف

0.59

клопе

0.57

 EconPapers

0.55

Hrsg

0.54

/\.

0.53

fazione

0.52

polazione

0.52

iedenis

0.51

inerie

0.51

ukunft

0.49

Activations Density 0.068%

references to specific titles and notable figures in academic or ideological contexts

No Comments

No Known Activations