INDEX

Explanations

conversational discourse markers and expressions of uncertainty or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

styleType

-0.52

ódó

-0.49

StructEnd

-0.49

uxxxx

-0.48

+};

-0.48

onAttach

-0.47

خصة

-0.47

umque

-0.47

https

-0.44

 granddaughter

-0.42

POSITIVE LOGITS

 lest

0.66

不然

0.64

 ujednoznacz

0.60

 otherwise

0.60

 Otherwise

0.58

astrous

0.56

 Preferably

0.56

posables

0.56

以免

0.56

 Normdatei

0.55

Activations Density 0.328%

conversational discourse markers and expressions of uncertainty or preference

No Comments

No Known Activations