INDEX

Explanations

code-related constructs and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

permum

-0.48

 uintptr

-0.47

 Owners

-0.47

 Somers

-0.47

ionView

-0.47

上角

-0.45

nativeElement

-0.45

 Siehe

-0.44

seteq

-0.43

 Second

-0.43

POSITIVE LOGITS

ImageContext

0.85

expandindo

0.82

AutoresizingMask

0.77

IndentedString

0.76

WaitGroup

0.76

verwijspagina

0.74

Demografía

0.73

 समीक्षाओं

0.69

 AssemblyCulture

0.66

Enllaces

0.63

Activations Density 0.414%

code-related constructs and expressions

No Comments

No Known Activations