INDEX

Explanations

key concepts related to data structure, representation, and criteria for evaluation or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

μισ

-0.59

vedic

-0.59

 RequestMethod

-0.58

ázaro

-0.58

 médicaux

-0.57

ResumeLayout

-0.57

 مرئيه

-0.55

BIND

-0.55

 contextLoads

-0.54

 Murch

-0.53

POSITIVE LOGITS

WireFormatLite

0.70

netbeans

0.61

 would

0.56

 createState

0.56

 alone

0.55

 will

0.52

 /\.(

0.51

FirstResponder

0.51

roek

0.51

 pinulongan

0.51

Activations Density 0.773%

key concepts related to data structure, representation, and criteria for evaluation or classification

No Comments

No Known Activations