INDEX

Explanations

terms related to legal and penal conditions or scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.56

ształ

-0.48

utilisons

-0.47

 içi

-0.47

RectangleBorder

-0.46

openConnection

-0.46

 contactos

-0.44

ProgressHUD

-0.43

 références

-0.43

новништво

-0.42

POSITIVE LOGITS

 center

1.23

 room

1.22

 rooms

1.21

 houſe

1.11

 centre

1.10

room

1.09

 house

1.09

 station

1.07

house

1.05

 facility

1.01

Activations Density 0.546%

terms related to legal and penal conditions or scenarios

No Comments

No Known Activations