INDEX

Explanations

occurrences of numbers or values

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

InjectAttribute

-0.75

 nonUne

-0.70

Xna

-0.70

 pinulongan

-0.68

 newOwner

-0.68

出版年

-0.65

aarrggbb

-0.63

KommentareTeilen

-0.63

WillAppear

-0.62

Personendaten

-0.60

POSITIVE LOGITS

THIS

0.63

this

0.56

본

0.56

This

0.54

 THIS

0.54

본

0.52

DebuggerNonUser

0.49

andaag

0.48

temon

0.46

FirebaseDatabase

0.45

Activations Density 0.290%

occurrences of numbers or values

No Comments

No Known Activations