INDEX

Explanations

tokens related to references or indications of medical context

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

SharedCtor

-0.76

 кӀ

-0.69

NewUrlParser

-0.66

...".

-0.64

astéro

-0.64

...",

-0.63

 bezeichneter

-0.63

 للمعارف

-0.61

 ſever

-0.60

webElementXpaths

-0.60

POSITIVE LOGITS

脚注の使い方

0.56

########.

0.52

 Waray

0.52

contentLoaded

0.51

tvguidetime

0.51

Παραπομπές

0.49

khó

0.48

 intégrée

0.47

 AspNetCore

0.47

ysz

0.46

Activations Density 0.498%

tokens related to references or indications of medical context

No Comments

No Known Activations