INDEX

Explanations

information related to choices and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

CreateModel

-0.65

脚注の使い方

-0.60

noinspection

-0.56

kháu

-0.54

دانشنامهٔ

-0.53

 onstage

-0.52

huriyet

-0.52

%>%

-0.51

 Inhabitants

-0.51

awtextra

-0.51

POSITIVE LOGITS

 FontFamily

0.60

 دیکھیے

0.59

tagHelperRunner

0.58

dard

0.54

 Legal

0.51

 PARTNERS

0.51

 незавершена

0.50

eens

0.49

nologie

0.49

 Paglinawan

0.48

Activations Density 0.547%

information related to choices and comparisons

No Comments

No Known Activations