INDEX

Explanations

specific locations and associated contexts

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

runOnUiThread

-0.56

日閲覧

-0.52

/\.

-0.50

الحياه

-0.49

 تعدى

-0.49

 leading

-0.48

 стаття

-0.48

ssysteme

-0.47

seits

-0.47

 studio

-0.46

POSITIVE LOGITS

OGND

0.84

 للاسماء

0.71

出版年

0.61

thâu

0.60

 CreateTagHelper

0.59

userdetails

0.58

/**

0.57

({},

0.56

 scattata

0.56

tvguidetime

0.56

Activations Density 0.284%

specific locations and associated contexts

No Comments

No Known Activations