INDEX

Explanations

terms and phrases related to biological and medical concepts, particularly in cancer research and immunotherapy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

rungsseite

-0.92

 تانيه

-0.72

-0.69

Билгалдахарш

-0.67

 kasarigan

-0.67

 الحره

-0.67

iibo

-0.63

 calendriers

-0.61

uesia

-0.61

XmlEnum

-0.60

POSITIVE LOGITS

 dianteira

0.56

 dianteiro

0.54

 høy

0.54

 traseiro

0.54

 pescoço

0.54

 forskjellige

0.51

 sogenannten

0.50

::::::::

0.50

 fleste

0.50

assorted

0.49

Activations Density 1.411%

terms and phrases related to biological and medical concepts, particularly in cancer research and immunotherapy

No Comments

No Known Activations