INDEX

Explanations

references to scientific terms and variables related to studies and measurements

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

igshid

-0.56

ThemeOverlay

-0.55

GrantedAuthority

-0.54

 nahilalakip

-0.52

 يتيمه

-0.51

 समीक्षाओं

-0.50

 Silla

-0.49

حر

-0.47

SetBool

-0.47

onoi

-0.46

POSITIVE LOGITS

CP

1.35

DP

1.33

RP

1.31

RP

1.28

DP

1.27

BP

1.25

FP

1.25

CP

1.25

BP

1.24

EP

1.24

Activations Density 0.695%

references to scientific terms and variables related to studies and measurements

No Comments

No Known Activations