INDEX

Explanations

references to testing or evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 تضيفلها

-0.75

+#+

-0.72

PostInfinity

-0.65

MemoryWarning

-0.64

ंदीखरीदारी

-0.63

 jspb

-0.63

 ब्रेकडाउन

-0.62

ModelSerializer

-0.60

 protoimpl

-0.60

CppMethod

-0.59

POSITIVE LOGITS

ximately

0.33

 Aplikasi

0.33

gunaan

0.33

Tok

0.32

ksamkeit

0.31

 doon

0.31

 encontrará

0.31

前任

0.31

 årets

0.31

 undersø

0.30

Activations Density 0.549%

references to testing or evaluation processes

No Comments

No Known Activations