INDEX

Explanations

occurrences of verbs related to actions and states of being, particularly in contexts involving decline, confusion, or existential questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ourselves

-0.77

 yourself

-0.77

 myself

-0.66

 himself

-0.66

ContentAsync

-0.65

 estekak

-0.62

DJANGO

-0.61

kháu

-0.60

Hozzáférés

-0.59

">//

-0.58

POSITIVE LOGITS

 يتيمه

0.63

 accru

0.53

 ocurrir

0.50

 AsyncTask

0.49

ArgsConstructor

0.48

 occur

0.48

occurs

0.48

 accrue

0.47

 Assumption

0.46

 occurs

0.46

Activations Density 0.079%

occurrences of verbs related to actions and states of being, particularly in contexts involving decline, confusion, or existential questions

No Comments

No Known Activations