INDEX

Explanations

medical or scientific terminology related to immunology and therapeutic applications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 investigators

-0.68

 Investigators

-0.63

 PMID

-0.61

 Penelitian

-0.61

 nogal

-0.61

 investigator

-0.60

 EXPERIMENTAL

-0.60

참고

-0.60

期刊论文

-0.60

 investigate

-0.59

POSITIVE LOGITS

 متعلقه

1.04

ftagPool

0.78

ImageContext

0.71

setVerticalGroup

0.70

oa̍t

0.68

IndentedString

0.67

 propOrder

0.66

EndGlobalSection

0.66

Gambas

0.62

NewUrlParser

0.61

Activations Density 6.616%

medical or scientific terminology related to immunology and therapeutic applications

No Comments

No Known Activations