INDEX

Explanations

occurrences of specific organizations, groups, or entities within a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

rrggbb

-0.79

 nahilalakip

-0.78

webElementXpaths

-0.65

MigrationBuilder

-0.60

Népesség

-0.59

 écl

-0.58

 marinho

-0.58

Чыганаклар

-0.56

 Normdatei

-0.56

Ecotoxicity

-0.55

POSITIVE LOGITS

 الحره

0.57

 Drapeau

0.56

 Serap

0.48

 forState

0.47

על

0.42

any

0.41

瘍

0.40

fr

0.39

liner

0.39

 Dép

0.39

Activations Density 2.336%

occurrences of specific organizations, groups, or entities within a given context

No Comments

No Known Activations