INDEX

Explanations

terms related to identity and existence

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

 betweenstory

-0.70

AndEndTag

-0.65

Obrázky

-0.63

 utafitiHapana

-0.62

ruptedException

-0.56

 forhold

-0.56

arschijnlijk

-0.55

 absl

-0.55

 getRequest

-0.55

^(@)

-0.54

POSITIVE LOGITS

 quien

1.54

who

1.51

Quien

1.32

who

1.29

Quem

1.22

 Quien

1.20

 quienes

1.20

 quem

1.19

Who

1.16

Whoever

1.16

Activations Density 0.161%

terms related to identity and existence

No Comments

No Known Activations