INDEX

Explanations

names of characters and their relationships in dialogues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 autorytatywna

-0.90

aarrggbb

-0.71

 שוליים

-0.68

ddots

-0.62

 ligiloj

-0.60

ituary

-0.59

httphttps

-0.58

Geplaatst

-0.58

ChildScrollView

-0.57

 Paglinawan

-0.57

POSITIVE LOGITS

 kissed

0.59

tagext

0.58

 mumbled

0.54

 fainted

0.53

 grinned

0.51

 jakiś

0.51

 leaned

0.50

thâu

0.50

 crouched

0.50

 protested

0.49

Activations Density 0.144%

names of characters and their relationships in dialogues

No Comments

No Known Activations