INDEX

Explanations

occurrences of names and terms relevant to demographics and social classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 pinulongan

-0.70

曖昧さ回避

-0.69

"],

-0.69

clable

-0.68

GraphicsUnit

-0.64

ός

-0.63

rahi

-0.63

ntown

-0.60

 CreateTagHelper

-0.58

 Legge

-0.58

POSITIVE LOGITS

PYX

0.65

 kasarigan

0.63

 StatelessWidget

0.59

 Wherefore

0.54

 colorés

0.54

thâu

0.53

 betweenstory

0.52

AutoScale

0.51

ostante

0.50

 giud

0.49

Activations Density 0.344%

occurrences of names and terms relevant to demographics and social classification

No Comments

No Known Activations