INDEX

Explanations

references to rewards and incentives related to performance or achievement

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

IsMutable

-0.85

Sucesor

-0.63

CppMethod

-0.63

OGND

-0.61

Personendaten

-0.58

</thead>

-0.56

 propOrder

-0.54

nodoc

-0.54

UserScript

-0.53

"}>

-0.50

POSITIVE LOGITS

0.58

Poloha

0.58

Становништво

0.51

 ventre

0.49

 gradova

0.47

JNIEnv

0.46

istung

0.46

ROIT

0.45

 bağlı

0.44

 Inhalten

0.44

Activations Density 0.371%

references to rewards and incentives related to performance or achievement

No Comments

No Known Activations