INDEX

Explanations

terms related to biological and medical contexts, particularly focusing on leukins and various health conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 morire

-0.69

 ویکی‌پدیا

-0.69

 lavoratori

-0.68

 Bioaccumulative

-0.67

 piú

-0.64

 répondit

-0.64

 figliu

-0.63

อาด

-0.62

tagHelperRunner

-0.62

 dovre

-0.62

POSITIVE LOGITS

 kasarigan

0.59

clerview

0.58

tonsoft

0.57

 Breslau

0.57

 care

0.56

quelize

0.55

ILayout

0.53

sunami

0.53

uitton

0.52

edipus

0.50

Activations Density 1.262%

terms related to biological and medical contexts, particularly focusing on leukins and various health conditions

No Comments

No Known Activations