INDEX

Explanations

technical terms related to engine design and functionality

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

enumi

-0.52

în

-0.49

 commissioners

-0.47

 Gummies

-0.47

 sedia

-0.47

bibli

-0.47

 sebe

-0.46

</blockquote>

-0.46

 hosted

-0.45

 Movers

-0.45

POSITIVE LOGITS

WriteTagHelper

0.76

 MenuView

0.74

dafx

0.72

 ThemeData

0.70

 Савезне

0.70

 /\.(

0.67

ządu

0.67

SuppressMessage

0.66

 fuel

0.65

DebuggerNonUser

0.64

Activations Density 0.286%

technical terms related to engine design and functionality

No Comments

No Known Activations