INDEX

Explanations

references to data parsing and JSON manipulation

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

bers

-0.49

σα

-0.49

BeginInit

-0.46

 Borel

-0.45

hap

-0.44

хьтан

-0.43

uyla

-0.42

jonen

-0.41

 prenez

-0.41

enden

-0.40

POSITIVE LOGITS

 home

0.81

 OMITBAD

0.73

 وتسجيلات

0.73

elemField

0.72

nodoc

0.70

AccessorTable

0.70

ioutil

0.67

InjectAttribute

0.64

Home

0.63

LookAnd

0.63

Activations Density 0.147%

references to data parsing and JSON manipulation

No Comments

No Known Activations