INDEX

Explanations

programming-related keywords and concepts, particularly in Java and web development frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

zor

-0.51

must

-0.50

 Skyl

-0.50

jal

-0.49

Bew

-0.46

산

-0.45

Jal

-0.45

Dok

-0.45

AMAN

-0.45

テン

-0.44

POSITIVE LOGITS

UseVisualStyle

5.57

IsContent

1.42

UrlResolution

1.30

GraphicsUnit

1.29

 IBOutlet

1.16

TabStop

1.14

новништво

1.12

enterOuterAlt

1.10

UnusedPrivate

1.05

AutoScaleMode

1.04

Activations Density 0.003%

programming-related keywords and concepts, particularly in Java and web development frameworks

No Comments

No Known Activations