INDEX

Explanations

terms indicating frequency or commonality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 kaarangay

-0.75

DllImport

-0.69

 دیکھیے

-0.68

KELEY

-0.66

DockStyle

-0.64

 ddelweddau

-0.64

 AppModule

-0.60

CDCl

-0.58

WriteLiteral

-0.56

 JSTOR

-0.56

POSITIVE LOGITS

Datuak

0.71

 насељу

0.68

enschappelijke

0.63

ftagPool

0.61

iest

0.58

 closest

0.57

तम

0.55

这一次

0.53

ctory

0.53

Réponse

0.53

Activations Density 0.153%

terms indicating frequency or commonality

No Comments

No Known Activations