INDEX

Explanations

names and affiliations in an academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

ManagedBean

-0.55

setupUi

-0.53

UserScript

-0.52

 Perp

-0.51

afficheront

-0.50

 useContext

-0.49

queryInterface

-0.47

 Rank

-0.47

 mắn

-0.46

 Pelleg

-0.46

POSITIVE LOGITS

Lim

0.68

Nor

0.65

IndentedString

0.63

Ong

0.59

Nor

0.57

Az

0.57

Lim

0.56

pun

0.56

Ng

0.56

Low

0.55

Activations Density 0.973%

names and affiliations in an academic context

No Comments

No Known Activations