INDEX

Explanations

individual characters or small sequences in a data structure or code segment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 neutre

-0.57

 faveur

-0.53

ότη

-0.52

 Seren

-0.52

Torna

-0.49

 leaſt

-0.48

 polynomials

-0.48

 JComboBox

-0.47

 GetData

-0.47

xnn

-0.47

POSITIVE LOGITS

لينكات

0.75

 transfieras

0.65

Билгалдахарш

0.61

发表于

0.60

 الاطلاع

0.60

 transférez

0.59

\{\\

0.59

RegressionTest

0.59

脚注の使い方

0.58

AddTagHelper

0.57

Activations Density 0.125%

individual characters or small sequences in a data structure or code segment

No Comments

No Known Activations