INDEX

Explanations

phrases related to algorithms and programming structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 digress

-0.60

Hochspringen

-0.56

MemoryWarning

-0.55

 NUKAT

-0.47

.)

-0.47

 jelasnya

-0.47

 embri

-0.45

Entry

-0.44

込んで

-0.44

 nonUne

-0.43

POSITIVE LOGITS

DebuggerNonUser

0.68

 protoimpl

0.65

CompilerServices

0.64

 оригіналу

0.63

 GenerationType

0.63

 Referential

0.60

 متحده

0.58

copg

0.58

 Periodicals

0.56

 unattended

0.56

Activations Density 0.073%

phrases related to algorithms and programming structures

No Comments

No Known Activations