INDEX

Explanations

event-related coverage involving notable individuals and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

UseVisualStyle

-0.72

stående

-0.58

erals

-0.52

 Fiche

-0.52

 anggaran

-0.51

 Fests

-0.50

iedział

-0.49

 تانيه

-0.49

FindAll

-0.48

 Entsch

-0.47

POSITIVE LOGITS

 joined

0.78

 joins

0.74

 join

0.73

 perform

0.70

 performing

0.68

 narr

0.68

 giving

0.66

 joining

0.65

 kasarigan

0.65

 answer

0.64

Activations Density 0.133%

event-related coverage involving notable individuals and activities

No Comments

No Known Activations