INDEX

Explanations

the presence of the word "in" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ersdorf

-0.64

rot

-0.61

rotz

-0.59

 Marl

-0.53

giu

-0.52

امية

-0.52

 Basi

-0.52

 glutamate

-0.52

luc

-0.51

bewerken

-0.51

POSITIVE LOGITS

GOTREF

0.81

']))

0.74

 incomplète

0.70

خخ

0.67

?}",

0.66

})*/

0.64

seamnă

0.63

 émer

0.62

ResumeLayout

0.62

:=

0.62

Activations Density 0.043%

the presence of the word "in" in various contexts

No Comments

No Known Activations