INDEX

Explanations

references to specific areas, metrics, or elements within a structured or technical context

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

VIAF

-0.78

 tartalomajánló

-0.73

BufferException

-0.72

ReusableCell

-0.69

InjectAttribute

-0.69

 NSCoder

-0.69

uxxxx

-0.68

 defaultstate

-0.68

ChildScrollView

-0.67

 propOrder

-0.66

POSITIVE LOGITS

↵↵

0.62

0.53

The

0.52

0.50

the

0.49

Item

0.48

 these

0.47

in

0.47

 missing

0.46

 better

0.46

Activations Density 0.224%

references to specific areas, metrics, or elements within a structured or technical context

No Comments

No Known Activations