INDEX

Explanations

terms related to occupation and control, especially in a historical or territorial context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ystemet

-0.58

Big

-0.54

big

-0.53

Big

-0.52

bogen

-0.50

big

-0.50

勁

-0.49

스템

-0.49

BIG

-0.48

 mög

-0.48

POSITIVE LOGITS

 occupied

1.84

occupied

1.75

 occupation

1.75

 occup

1.73

 OCCUP

1.71

 occupa

1.68

 occupy

1.68

 Occupied

1.64

 Occupation

1.64

occup

1.63

Activations Density 0.143%

terms related to occupation and control, especially in a historical or territorial context

No Comments

No Known Activations