INDEX

Explanations

references to biological or medical entities and details within research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalColumn

-0.71

PreferredItem

-0.66

 мәкал

-0.63

WriteBarrier

-0.63

niająca

-0.61

 للاسماء

-0.58

 فريبيس

-0.55

Diweddarwch

-0.55

expandindo

-0.53

 soort

-0.53

POSITIVE LOGITS

 {}));

0.62

 particulières

0.61

 nakalista

0.60

>>();

0.57

 particulier

0.52

 righe

0.50

 spos

0.49

'));

0.49

｀*)

0.49

 particulière

0.48

Activations Density 1.948%

references to biological or medical entities and details within research contexts

No Comments

No Known Activations