INDEX

Explanations

references to specific programming or computing concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Gweler

-0.55

 conventional

-0.52

setMap

-0.50

(?:

-0.48

 parent

-0.48

+:+

-0.48

ập

-0.47

Gambas

-0.46

istus

-0.46

getMap

-0.46

POSITIVE LOGITS

tagHelperRunner

0.84

PerformLayout

0.73

 createContext

0.69

 ujednoznacz

0.68

 дописавши

0.64

HostException

0.63

 bezeichneter

0.62

 oprot

0.61

Nuo

0.61

 propOrder

0.61

Activations Density 0.029%

references to specific programming or computing concepts

No Comments

No Known Activations