INDEX

Explanations

references to the concept of 'mental states' or 'mental processes'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Wikispecies

-0.60

úly

-0.58

FontOfSize

-0.55

 soigne

-0.53

 Verenig

-0.52

 dAtA

-0.52

 aveug

-0.51

Jä

-0.50

hå

-0.49

][:

-0.49

POSITIVE LOGITS

ment

3.39

ments

3.04

MENT

2.73

MENTS

2.40

 ment

1.91

EMENT

1.80

メント

1.69

Ment

1.68

mente

1.67

mento

1.59

Activations Density 0.040%

references to the concept of 'mental states' or 'mental processes'

No Comments

No Known Activations

references to the concept of 'mental states' or 'mental processes'

No Comments

No Known Activations