INDEX

Explanations

references to male characters or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Gambas

-0.59

Personensuche

-0.57

 pinulongan

-0.53

 calico

-0.50

biam

-0.50

CloseOperation

-0.49

EDEFAULT

-0.47

 layui

-0.47

Timezone

-0.46

 maji

-0.45

POSITIVE LOGITS

 himself

1.10

hehe

0.98

hehehe

0.94

himself

0.92

’

0.85

eding

0.83

too

0.80

 stesso

0.79

0.77

 Himself

0.75

Activations Density 0.177%

references to male characters or individuals

No Comments

No Known Activations