INDEX

Explanations

references to associations or connections with others, especially in a supportive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

chapper

-0.52

Datuak

-0.51

UnknownFieldSet

-0.51

程度上

-0.51

landaise

-0.50

 Nightmare

-0.49

мум

-0.48

unta

-0.48

ynie

-0.48

 frantically

-0.48

POSITIVE LOGITS

Tikang

0.69

yntaxException

0.65

andExpect

0.62

NameInMap

0.61

 defaultstate

0.61

detectChanges

0.55

AndEndTag

0.53

neté

0.53

EndProject

0.50

 IBOutlet

0.50

Activations Density 0.220%

references to associations or connections with others, especially in a supportive context

No Comments

No Known Activations