INDEX

Explanations

numerical data or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

});*/

-0.61

()?;

-0.58

MockMvc

-0.56

IFA

-0.56

dflare

-0.56

)•

-0.56

anmoins

-0.56

SizeF

-0.55

ServiceModel

-0.55

 Baillargeon

-0.55

POSITIVE LOGITS

GraphicsUnit

0.66

 zvuky

0.64

intios

0.63

addPreferredGap

0.60

wikidata

0.57

ValueStyle

0.57

WithMany

0.57

 yawn

0.55

IsPostBack

0.55

gypti

0.55

Activations Density 0.041%

numerical data or counts

No Comments

No Known Activations