INDEX

Explanations

terms related to immunology and statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 rospy

-0.57

 okhttp

-0.52

 MonoBehaviour

-0.47

 Wicidata

-0.47

力は

-0.45

Linki

-0.45

addCriterion

-0.44

antMatchers

-0.43

unay

-0.43

原始内容存档于

-0.43

POSITIVE LOGITS

 standpoint

1.10

 perspective

0.84

 onwards

0.84

 vantage

0.76

 sources

0.75

مصادر

0.73

 kaynağından

0.71

 perspectives

0.67

 otomatig

0.67

perspective

0.62

Activations Density 0.471%

terms related to immunology and statistical analysis

No Comments

No Known Activations