INDEX

Explanations

specific identifiers or numerical values that suggest categories or classifications in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 kaynağından

-0.58

 Waray

-0.56

ExecuteReader

-0.52

########.

-0.50

 invester

-0.49

ugges

-0.48

conom

-0.48

zeiti

-0.47

 विश्वसनीयता

-0.47

igshid

-0.46

POSITIVE LOGITS

thâu

0.66

下载附件

0.57

์

0.54

ngrx

0.53

formik

0.51

 createSprite

0.51

်း

0.51

 neuve

0.50

principalColumn

0.50

 للمعارف

0.49

Activations Density 0.727%

specific identifiers or numerical values that suggest categories or classifications in data

No Comments

No Known Activations