INDEX

Explanations

statements related to function returns

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

 NDEBUG

-0.63

 itſelf

-0.62

 فريبيس

-0.55

 venons

-0.54

 ddelweddau

-0.54

 TMPro

-0.52

*++

-0.51

 cdti

-0.49

 Ceux

-0.48

 Mojave

-0.48

POSITIVE LOGITS

 مشين

1.05

ंदीखरीदारी

0.98

 snippetHide

0.91

addGap

0.87

istoitu

0.82

findpost

0.80

WebVitals

0.79

stateMutability

0.74

sizeCache

0.74

Autoritní

0.74

Activations Density 0.040%

statements related to function returns

No Comments

No Known Activations