INDEX

Explanations

references to reviews or articles

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

"Read our full review"

np_acts-logits-general · gemini-2.0-flash

Read our

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

tagHelperRunner

-0.57

InstanceState

-0.50

 estekak

-0.49

SerializedSize

-0.49

HttpPost

-0.48

 Engel

-0.48

RegressionTest

-0.47

 <!--

-0.46

 pekan

-0.46

WireFormatLite

-0.45

POSITIVE LOGITS

moveToFirst

0.65

èdia

0.58

 SDLK

0.57

IBinder

0.55

 Профиль

0.55

 Coss

0.55

SPECIFICATIONS

0.55

 Signalez

0.54

 onBackPressed

0.54

 JTable

0.53

Activations Density 0.040%

references to reviews or articles

"Read our full review"

Read our

No Comments

No Known Activations