INDEX

Explanations

references to data segmentation or division into smaller units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 ModelExpression

-0.71

Politique

-0.70

 actionMode

-0.67

CloseOperation

-0.66

esez

-0.65

новниш

-0.62

sizeCache

-0.61

iocene

-0.60

 sumpay

-0.60

MENAFN

-0.59

POSITIVE LOGITS

 quæ

0.63

 themſelves

0.57

 cioè

0.55

 subterrá

0.54

 itſelf

0.54

 تضيفلها

0.54

 individuale

0.53

 separados

0.52

neſs

0.49

 autorytatywna

0.48

Activations Density 0.542%

references to data segmentation or division into smaller units

No Comments

No Known Activations