INDEX

Explanations

references to justifications in moral or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

prepareStatement

-0.41

PreferredItem

-0.37

UserScript

-0.36

 كومونز

-0.36

OpenHelper

-0.35

InitVars

-0.35

 remember

-0.34

ThroughAttribute

-0.34

endforeach

-0.34

 censiti

-0.34

POSITIVE LOGITS

 justification

1.44

 justifies

1.32

 justify

1.30

 Justification

1.30

 justified

1.30

 justifying

1.24

 gius

1.18

 justific

1.16

Justification

1.14

 excuse

1.13

Activations Density 0.699%

references to justifications in moral or legal contexts

No Comments

No Known Activations