INDEX

Explanations

references to authorities and their judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 doInBackground

-0.82

gonic

-0.75

 Wiktionnaire

-0.74

 виправивши

-0.69

tableFuture

-0.69

ſy

-0.69

ंदीखरीदारी

-0.68

mybatisplus

-0.68

openConnection

-0.68

 ſmall

-0.67

POSITIVE LOGITS

于是

0.43

ServiceProvider

0.41

 deemed

0.40

 balles

0.40

 behov

0.39

 deem

0.38

Derbyniad

0.37

 Merz

0.37

 estekak

0.37

so

0.37

Activations Density 0.588%

references to authorities and their judgments

No Comments

No Known Activations