INDEX

Explanations

references to individuals, organizations, and political activities

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

brainly

-0.61

 himo

-0.53

didSet

-0.51

ställning

-0.51

IZEN

-0.50

clientY

-0.50

niest

-0.50

Cik

-0.49

ơn

-0.48

sendFile

-0.48

POSITIVE LOGITS

tisseur

0.60

HasBeenSet

0.59

__*/

0.59

EndContext

0.56

again

0.53

tableFuture

0.51

Geplaatst

0.50

\]

0.50

red

0.49

AGAIN

0.49

Activations Density 0.086%

references to individuals, organizations, and political activities

No Comments

No Known Activations