INDEX

Explanations

terms related to efficiency and performance metrics

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

ending in "ff" followed by other various letters

np_acts-logits-general · gemini-2.0-flash

words ending in uff or off

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

er

-0.94

ER

-0.69

osene

-0.64

enumi

-0.62

béco

-0.61

 CascadeType

-0.60

rungsseite

-0.58

verwijspagina

-0.57

prelude

-0.56

جمعیت

-0.56

POSITIVE LOGITS

 Tuff

0.77

Coff

0.68

 paff

0.68

 Puff

0.67

Sif

0.66

 poff

0.66

yf

0.63

Uff

0.62

fff

0.62

 tuff

0.60

Activations Density 0.518%

terms related to efficiency and performance metrics

ending in "ff" followed by other various letters

words ending in uff or off

No Comments

No Known Activations