INDEX

Explanations

the letter 't' in various contexts

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

ending in "t" followed by a vowel

np_acts-logits-general · gemini-2.0-flash

words starting with t followed by specific endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AssemblyCompany

-0.64

TypedDataSet

-0.60

addContainerGap

-0.59

NamedQueries

-0.57

InSection

-0.57

sidemargin

-0.57

drawSprites

-0.56

errHandler

-0.55

adə

-0.52

LookAnd

-0.52

POSITIVE LOGITS

ite

0.53

ucker

0.49

انيف

0.49

tagext

0.49

ate

0.48

paksa

0.48

ade

0.48

ave

0.45

iz

0.45

例文帳に追加

0.44

Activations Density 0.169%

the letter 't' in various contexts

ending in "t" followed by a vowel

words starting with t followed by specific endings

No Comments

No Known Activations