INDEX

Explanations

terms related to functionality and actions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

enumi

-0.73

 mieli

-0.55

 byli

-0.54

 సౌకర్య

-0.54

 taken

-0.54

__((

-0.52

íncia

-0.51

 born

-0.50

 मिले

-0.50

HasForeignKey

-0.50

POSITIVE LOGITS

Was

0.67

Was

0.59

ztály

0.52

was

0.50

CloseOperation

0.49

Wasn

0.49

deva

0.48

HAS

0.48

Has

0.48

ði

0.48

Activations Density 0.041%

terms related to functionality and actions in programming contexts

No Comments

No Known Activations