INDEX

Explanations

expressions of agreement or consensus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ***!

-0.49

 téléphonique

-0.48

Handlung

-0.47

tituts

-0.46

__(/*!

-0.46

empuan

-0.46

chnet

-0.45

 piacere

-0.45

 acompaña

-0.43

 mattered

-0.43

POSITIVE LOGITS

stateProvider

0.75

webElementXpaths

0.72

الدراسه

0.71

principalTable

0.71

__":

0.68

RetentionPolicy

0.67

 ivelany

0.67

cèse

0.66

 RSSSF

0.66

 agree

0.65

Activations Density 0.119%

expressions of agreement or consensus

No Comments

No Known Activations