INDEX

Explanations

dialogue and expressions of communication between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

ˈ

-0.50

orphic

-0.47

 follicular

-0.47

odle

-0.44

ztat

-0.44

 abstinence

-0.43

ByExample

-0.43

oo

-0.41

örper

-0.41

 /\.(

-0.41

POSITIVE LOGITS

AndEndTag

1.13

UnusedPrivate

0.78

NameInMap

0.77

তথ্যসূত্র

0.72

HostException

0.72

Geplaatst

0.72

 وتسجيلات

0.71

 noDo

0.70

Personendaten

0.69

IBarButtonItem

0.69

Activations Density 0.384%

dialogue and expressions of communication between characters

No Comments

No Known Activations