INDEX

Explanations

acknowledgments and expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 "..\..\..\

-0.74

 "..\..\

-0.71

RuleContext

-0.67

antd

-0.66

Diweddarwch

-0.65



-0.63

ModelSerializer

-0.63

Péri

-0.62

Autoritní

-0.57

LookAnd

-0.56

POSITIVE LOGITS

izr

0.59

 geleverd

0.57

 selfless

0.56

 incroy

0.53

 THANK

0.51

 brave

0.51

rateful

0.51

 Thank

0.50

 phénom

0.50

 accomplishments

0.49

Activations Density 0.241%

acknowledgments and expressions of gratitude

No Comments

No Known Activations