INDEX

Explanations

occurrences of the word "in."

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

"In fact" or "In [location]" introducing a clause

np_acts-logits-general · gemini-2.0-flash

in fact

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

onViewCreated

-0.52

 MonoBehaviour

-0.51

setopt

-0.50

offsetHeight

-0.50

getColumnIndex

-0.50

 variously

-0.50

offsetWidth

-0.50

 widely

-0.48

OnAdd

-0.48

parseDouble

-0.48

POSITIVE LOGITS

case

0.89

 initComponents

0.72

 '\\;'

0.65

 regards

0.65

 anyway

0.62

till

0.62

 case

0.60

NonQuery

0.59

 nakalista

0.58

 anyways

0.58

Activations Density 0.320%

occurrences of the word "in."

"In fact" or "In [location]" introducing a clause

in fact

No Comments

No Known Activations