INDEX

Explanations

terms related to schema definitions and technical specifications

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

IVEREF

-0.84

 initComponents

-0.79

 Jefus

-0.74

WithIOException

-0.72

 Monfieur

-0.72

 itſelf

-0.70

 myſelf

-0.70

shund

-0.69

 feroit

-0.68

 tartalomajánló

-0.68

POSITIVE LOGITS

CascadeType

0.48

↵↵

0.47

quelize

0.46

 bodyParser

0.45

 viewDidLoad

0.43

‚¬

0.43

 living

0.43

who

0.42

 morto

0.42

</i>

0.41

Activations Density 0.004%

terms related to schema definitions and technical specifications

No Comments

No Known Activations