INDEX

Explanations

phrases related to looking or observing

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

 BorderRadius

-0.66

ΕΝ

-0.61

GenerationType

-0.60

Coordonnées

-0.57

entuh

-0.57

twimg

-0.57

idać

-0.56

værende

-0.56

tehen

-0.55

nationality

-0.54

POSITIVE LOGITS

tvguidetime

0.56

 createState

0.55

okovic

0.54

Geplaatst

0.54

AlterField

0.53

Hochspringen

0.50

MLLoader

0.47

رشف

0.46

 initComponents

0.46

QMetaType

0.44

Activations Density 0.159%

phrases related to looking or observing

No Comments

No Known Activations