INDEX

Explanations

different specifications of size in a programming or data context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ரும்

-0.57

eaways

-0.55

ueroa

-0.54

 Cuatro

-0.51

یدم

-0.51

 blasphemy

-0.51

upné

-0.50

 Hamp

-0.49

enangan

-0.48

 Palest

-0.48

POSITIVE LOGITS

Size

2.49

 Size

2.20

 size

1.87

 SIZE

1.84

SIZE

1.79

size

1.75

 sizes

1.47

 Sizes

1.45

awtextra

1.40

SizeF

1.34

Activations Density 0.036%

different specifications of size in a programming or data context

No Comments

No Known Activations