INDEX

Explanations

references to specific localities or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

tagHelperRunner

-0.57



-0.57

 WaitForSeconds

-0.54

 للمعارف

-0.49

цездатний

-0.49

sizeCache

-0.48

SourceChecksum

-0.48

 jsPsych

-0.46

Rohy

-0.46

IBOutlet

-0.45

POSITIVE LOGITS

 itself

0.38

illants

0.36

 envelope

0.35

altezza

0.35

itself

0.35

ึ่ง

0.34

abetes

0.33

요

0.32

 Envelope

0.32

 anvil

0.31

Activations Density 2.987%

references to specific localities or institutions

No Comments

No Known Activations