INDEX

Explanations

sections of text that signify results or conclusions in a study or article

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ReusableCell

-0.46

 الرياضيه

-0.46

EndContext

-0.44

Население

-0.44

 ddelweddau

-0.43

 frow

-0.43

ことなく

-0.43

insic

-0.41

 Egyptians

-0.39

муж

-0.39

POSITIVE LOGITS

 bezeichneter

0.98

httphttps

0.85

ंदीखरीदारी

0.78

 AssemblyCompany

0.76

发表于

0.73

 nodeId

0.72

upported

0.71

Portale

0.70

NUMX

0.69

 EconPapers

0.69

Activations Density 0.075%

sections of text that signify results or conclusions in a study or article

No Comments

No Known Activations