INDEX

Explanations

key terms related to emotional impact and critical reviews of films

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

Statements of cause and effect

np_acts-logits-general · gemini-2.0-flash

logical sequence indicators

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ExecuteAsync

-1.04

 HasFactory

-0.70

nanoTime

-0.63

WebMethod

-0.60

.*")]

-0.59

IntoConstraints

-0.58

MenuInflater

-0.58

̵

-0.57

featureID

-0.57

centiles

-0.56

POSITIVE LOGITS

 firstly

0.71

 recommand

0.71

 Besides

0.70

Ⅰ

0.69

Ⅱ

0.69

 accro

0.68

 equipments

0.65

NameInMap

0.64

Ⅲ

0.64

Besides

0.63

Activations Density 3.082%

key terms related to emotional impact and critical reviews of films

Statements of cause and effect

logical sequence indicators

No Comments

No Known Activations