INDEX

Explanations

personal names and identifiers in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 pēc

-0.47

 trava

-0.45

oa̍t

-0.43

 gynhyrchwyd

-0.43

Autoritní

-0.43

parseFrom

-0.41

buttonBar

-0.41

ksjon

-0.40

oustics

-0.40

 مشين

-0.40

POSITIVE LOGITS

RenderAtEndOf

0.82

참고

0.76

Datuak

0.72

:✨

0.71

 Vira

0.64

SuccessListener

0.64

 Majefty

0.63

 getopt

0.63

 endregion

0.63

 Anfitrión

0.63

Activations Density 0.159%

personal names and identifiers in the text

No Comments

No Known Activations