INDEX

Explanations

references to medical conditions or associated events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

vgili

-0.49

Viited

-0.49

 Administrativna

-0.48

blech

-0.46

 rumput

-0.45

Rüyada

-0.45

:+:

-0.44

Xna

-0.44

rovnik

-0.44

ğlık

-0.43

POSITIVE LOGITS

IsContent

0.84

Geplaatst

0.78

 <>",

0.73

 houſe

0.70

Efq

0.69

 ſta

0.68

ſelves

0.66

 myſelf

0.66

ſelf

0.65

enumii

0.65

Activations Density 0.973%

references to medical conditions or associated events

No Comments

No Known Activations