INDEX

Explanations

words related to actions or events involving physical changes or processing

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

 élevées

-0.58

 Bevölkerung

-0.51

has

-0.49

mainwindow

-0.49

ran

-0.48

 dục

-0.47

siga

-0.46

use

-0.46

hubungan

-0.46

make

-0.46

POSITIVE LOGITS

rungsseite

0.90

OGND

0.80

AddHtmlAttribute

0.68

tvguidetime

0.65

Datuak

0.63

thâu

0.62

__':

0.62

Legături

0.62

expandindo

0.61

transQ

0.61

Activations Density 0.870%

words related to actions or events involving physical changes or processing

No Comments

No Known Activations