INDEX

Explanations

the word "can" in various contexts, indicating capability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 '\\;'

-0.92

 kasarigan

-0.86

^(@)

-0.85

 Theſe

-0.84

хьтан

-0.79

Efq

-0.78

yaitu

-0.78

:✨

-0.77

requestCode

-0.77

 himſelf

-0.77

POSITIVE LOGITS

Puedo

0.61

 wider

0.59

hets

0.58

我可以

0.54

Yep

0.54

ußen

0.54

land

0.53

 podemos

0.53

 ACCOM

0.53

Yeah

0.53

Activations Density 0.126%

the word "can" in various contexts, indicating capability or possibility

No Comments

No Known Activations