INDEX

Explanations

elements related to mathematical or programming structures, including nodes, edges, and their properties in a defined system

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

 متعلقه

-0.69

setopt

-0.57

 fronte

-0.55

 تعدى

-0.53

mär

-0.52

 Guil

-0.50

 ujednoznacz

-0.49

لب

-0.48

 Vorge

-0.48

rö

-0.47

POSITIVE LOGITS

PerformLayout

0.73

kloped

0.67

windowFixed

0.65

 Exacts

0.65

OGND

0.61

ftagPool

0.61

rawDesc

0.61

 CreateTagHelper

0.58

 Paglinawan

0.57

matchCondition

0.56

Activations Density 0.468%

elements related to mathematical or programming structures, including nodes, edges, and their properties in a defined system

No Comments

No Known Activations