INDEX

Explanations

references to locations and time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 nahilalakip

-0.95

UserScript

-0.88

AppMethodBeat

-0.82

 виправивши

-0.81

OGND

-0.80

__':

-0.77

__":

-0.77

bitField

-0.74

 initComponents

-0.74

tagHelperRunner

-0.73

POSITIVE LOGITS

 inappropriate

0.63

appropriate

0.54

 opportune

0.54

 wrong

0.53

 justru

0.53

ino

0.51

 unexpectedly

0.50

wrong

0.50

harusnya

0.49

不该

0.48

Activations Density 0.221%

references to locations and time

No Comments

No Known Activations