INDEX

Explanations

references to time-related phrases and sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

GEBURTSDATUM

-1.01

Hentet

-0.75

edata

-0.70

 виправивши

-0.70

 Wikimédia

-0.68

 esetén

-0.65

 ujednoznacz

-0.64

 transfieras

-0.64

StoreMessageInfo

-0.63

 AspNetCore

-0.61

POSITIVE LOGITS

 thing

0.78

iniest

0.58

 amount

0.57

liest

0.57

AndroidJUnit

0.55

낌

0.51

 stuff

0.51

Eloquent

0.49

way

0.49

 kind

0.49

Activations Density 0.834%

references to time-related phrases and sequences

No Comments

No Known Activations