INDEX

Explanations

quantitative data and statistics related to experimental results

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

 preferências

-0.60

ẠI

-0.59

ChildScrollView

-0.57

pulumi

-0.56

 unknownFields

-0.55

Xaml

-0.51

 mußte

-0.51

MethodManager

-0.51

SVT

-0.50

 vendeurs

-0.50

POSITIVE LOGITS

Personensuche

0.68

SourceChecksum

0.65

hoeddwyd

0.61

!*\

0.57

 himo

0.57

 AppComponent

0.54

 Infórmanos

0.54

<bos>

0.54

ఔ

0.52

 Ninety

0.52

Activations Density 0.391%

quantitative data and statistics related to experimental results

No Comments

No Known Activations