INDEX

Explanations

terms related to generalizations and sample sizes in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

nościo

-0.56

zbęd

-0.52

 bezeichneter

-0.51

toHaveBeen

-0.51

 Klä

-0.51

matorium

-0.50

 competitor

-0.45

conflict

-0.45

 deinem

-0.44

 competing

-0.44

POSITIVE LOGITS

 generalization

0.83

 generalize

0.79

 generalizations

0.76

fillType

0.75

CppMethod

0.72

OGND

0.66

 generalized

0.65

Démographie

0.62

 general

0.61

eneral

0.60

Activations Density 0.732%

terms related to generalizations and sample sizes in research studies

No Comments

No Known Activations