INDEX

Explanations

references to figures in scientific texts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AspNetCore

-0.66

imageshack

-0.57

الحياه

-0.54

medy

-0.53

DropTable

-0.50

textTheme

-0.50

 credito

-0.49

otoro

-0.49

dersfield

-0.49

fortawesome

-0.48

POSITIVE LOGITS

 faſt

0.53

 Mile

0.53

oredCriteria

0.52

Билгалдахарш

0.52

0.51

 lenker

0.51

 Jefus

0.51

]=='

0.51

 Winaray

0.51

ſelves

0.50

Activations Density 0.177%

references to figures in scientific texts

No Comments

No Known Activations