INDEX

Explanations

references to software components or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

expandindo

-0.86

principalTable

-0.71

MessageOf

-0.71

 nahilalakip

-0.70

RegressionTest

-0.68

}\]

-0.68

MockBean

-0.67

oredCriteria

-0.66

Abitanti

-0.64

 betweenstory

-0.63

POSITIVE LOGITS

\{\\

0.67

 تضيفلها

0.52

amerikanischer

0.48

 Tart

0.47

—

0.47

 كومونز

0.47

uxxxx

0.47

 vastaan

0.46

[]"

0.45

 الحره

0.45

Activations Density 0.095%

references to software components or libraries

No Comments

No Known Activations