INDEX

Explanations

references to participants or entities involved in studies 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 @ 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

SequentialGroup

-0.65

AddTagHelper

-0.62

gameserver

-0.61

èdia

-0.60

ReusableCell

-0.57

lihood

-0.57

 समीक्षाओं

-0.56

::_('

-0.56

Datuak

-0.56

bewerken

-0.56

POSITIVE LOGITS

ibatis

0.54

مصادر

0.48

 quæ

0.48

ellschaft

0.48

anlage

0.48

who

0.47

cinta

0.47

來說

0.46

 modrá

0.45

 sendiri

0.45

Activations Density 0.714%

references to participants or entities involved in studies or events

No Comments

No Known Activations