INDEX

Explanations

terms related to scientific discussions or technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Various

-0.70

exemple

-0.69

例えば

-0.69

example

-0.67

 Various

-0.65

 Например

-0.65

various

-0.64

 example

-0.64

各種

-0.62

Especially

-0.61

POSITIVE LOGITS

 المعيارى

0.83

 resourceCulture

0.72

CppMethod

0.71

 Baillargeon

0.70

 AssemblyCulture

0.70

хьтан

0.69

mybatisplus

0.69

SizeF

0.69

 EnglishChoose

0.68

 zvuky

0.68

Activations Density 0.158%

terms related to scientific discussions or technical specifications

No Comments

No Known Activations