INDEX

Explanations

pieces of code and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

んだろう

-0.48

effetto

-0.46

 ngang

-0.45

KU

-0.45

γωγ

-0.44

 dessus

-0.44

intérieur

-0.44

 gangen

-0.43

ÁL

-0.43

Bu

-0.43

POSITIVE LOGITS

ngdoc

0.98

MemoryWarning

0.95

 AssemblyProduct

0.95

 lenker

0.94

parsedMessage

0.92

 propOrder

0.92

ValueStyle

0.91

ItemBackground

0.88

PreferredItem

0.81

expandindo

0.81

Activations Density 0.380%

pieces of code and programming constructs

No Comments

No Known Activations