INDEX

Explanations

programming constructs and syntax elements

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

AutoresizingMask

-0.49

scriptcase

-0.46

abinieri

-0.44

 ytterligare

-0.42

раздо

-0.42

sslich

-0.42

unjang

-0.41

씀

-0.40

 للاسماء

-0.40

 للمعارف

-0.40

POSITIVE LOGITS

int

2.38

int

2.23

Int

1.77

Int

1.73

 integer

1.63

INT

1.53

 Integer

1.52

INT

1.51

Integer

1.49

integer

1.38

Activations Density 0.388%

programming constructs and syntax elements

No Comments

No Known Activations