INDEX

Explanations

locations or contexts where actions occur

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

"in"

np_acts-logits-general · gemini-2.0-flash

preposition in

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CodeAttribute

-0.65

rawDesc

-0.61

}{@

-0.61

retum

-0.61

CppMethod

-0.60

__*/

-0.58

İstinadlar

-0.56

__["

-0.55

bootstrapcdn

-0.55

tant

-0.55

POSITIVE LOGITS

 MatDialog

0.66

 dedans

0.63

 inlay

0.60

amssymb

0.55

ofire

0.54

tagHelperRunner

0.54

 Cæsar

0.54

iprot

0.54

checkin

0.54

URLEncoder

0.54

Activations Density 0.136%

locations or contexts where actions occur

"in"

preposition in

No Comments

No Known Activations