INDEX

Explanations

requests for assistance or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 autorytatywna

-0.65

 مشين

-0.59

 Chwiliwch

-0.58

Hauptartikel

-0.56

بندی

-0.53

NUMX

-0.53

 <<<<<<<<<<<<<<

-0.51

]]]

-0.50

 AttributeSet

-0.50

Решение

-0.50

POSITIVE LOGITS

 rospy

0.57

 betweenstory

0.56

 ActionBar

0.55

сти

0.54

 lccn

0.54

 missione

0.53

 ویکی‌پدیای

0.50

المكان

0.50

DMETHOD

0.49

erebbe

0.48

Activations Density 0.206%

requests for assistance or clarification

No Comments

No Known Activations