INDEX

Explanations

database and programming terms used in structured data representation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)";

-0.63

Chham

-0.61

"](

-0.60

COUVER

-0.59

 chi̍t

-0.59

localctx

-0.59

feitura

-0.56

()");

-0.56

']))

-0.56

--)

-0.56

POSITIVE LOGITS

 type

0.68

LinkId

0.65

0.64

type

0.63

CodeAttribute

0.63

Idd

0.60

Type

0.60

 varchar

0.59

 typelib

0.58

 JpaRepository

0.58

Activations Density 0.269%

database and programming terms used in structured data representation

No Comments

No Known Activations