INDEX

Explanations

frequent references to the Google APIs and libraries, particularly focusing on common classes and functions

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

 tartalomajánló

-1.13

 unknownFields

-1.10

expandindo

-0.98

complexContent

-0.97

AsUp

-0.90

 <>",

-0.90

 &___

-0.89

protoimpl

-0.89

CodedInputStream

-0.89



-0.89

POSITIVE LOGITS

google

1.14

 matplotlib

0.63

 google

0.62

 GOOGLE

0.59

PPR

0.57

Google

0.57

GOOGLE

0.57

 Jules

0.53

googleapis

0.52

 Google

0.51

Activations Density 0.068%

frequent references to the Google APIs and libraries, particularly focusing on common classes and functions

No Comments

No Known Activations