INDEX

Explanations

numerals and numerical expressions related to historical data or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 transfieras

-0.64

 wireType

-0.57

astéroïdes

-0.56

 disponibilités

-0.55

Filmografia

-0.53

цезда

-0.52

 opérateur

-0.51

ingress

-0.50

 pleaſure

-0.49

ыгана

-0.49

POSITIVE LOGITS

xiv

0.47

rąg

0.47

abetes

0.47

dec

0.45

sunter

0.45

GMENT

0.45

makeText

0.44

łbym

0.43

findpost

0.43

DeleteBehavior

0.42

Activations Density 0.242%

numerals and numerical expressions related to historical data or events

No Comments

No Known Activations