INDEX

Explanations

references to characters and their relationships within narratives

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

 дописавши

-0.63

 незавершена

-0.62

 nakalista

-0.61

 zewnętrzne

-0.59

mishes

-0.57

 itſelf

-0.57

ựa

-0.57

 '\\;'

-0.57

 Chwiliwch

-0.57

 disambiguazione

-0.56

POSITIVE LOGITS

astify

0.61

omitempty

0.47

 javafx

0.47

 Weise

0.46

lickr

0.45

Provincia

0.45

新た

0.45

Edm

0.44

Mə

0.44

Enfant

0.43

Activations Density 0.208%

references to characters and their relationships within narratives

No Comments

No Known Activations