INDEX

Explanations

references to legal cases and proceedings

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

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

 InputDecoration

-0.65

AutoScaleMode

-0.64

 MainAxisSize

-0.61

GOTREF

-0.60

:]:

-0.60

 الحره

-0.59

tagHelperRunner

-0.56

 חיצוניים

-0.55

UrlResolution

-0.54

 MaterialApp

-0.53

POSITIVE LOGITS

 conducted

0.71

 waged

0.71

 fought

0.68

win

0.64

 выигра

0.62

 ended

0.60

 outcome

0.60

 estekak

0.60

 involving

0.59

Personendaten

0.59

Activations Density 0.421%

references to legal cases and proceedings

No Comments

No Known Activations