INDEX

Explanations

references to citations and mentions of capabilities within a programming or technical context

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

 itself

-0.60

ExecuteReader

-0.53

ruptedException

-0.52

 físicos

-0.50

 quelli

-0.49

 commerciaux

-0.49

/>;

-0.47

 concernés

-0.47

 Estos

-0.45

 rojos

-0.44

POSITIVE LOGITS

 Majefty

0.64

יהם

0.63

Nuevas

0.61

makeConstraints

0.60

 Affiliations

0.60

ianas

0.59

 sisters

0.59

 које

0.59

SharedCtor

0.57

 himſelf

0.57

Activations Density 0.016%

references to citations and mentions of capabilities within a programming or technical context

No Comments

No Known Activations