INDEX

Explanations

confirmation and verification-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

LayoutStyle

-0.51

exec

-0.48

retweeted

-0.48

ங்கு

-0.46

 spot

-0.43

 eint

-0.43

maría

-0.43

ish

-0.42

et

-0.41

 Cancelar

-0.41

POSITIVE LOGITS

AddTagHelper

0.67

 kasarigan

0.67

collected

0.66

WebMethod

0.65

 BitmapFactory

0.61

ilosop

0.60

himura

0.59

ensacola

0.59

queryInterface

0.58

taken

0.58

Activations Density 0.035%

confirmation and verification-related terms

No Comments

No Known Activations