INDEX

Explanations

phrases related to legality and ethical standards in behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

BaseAdapter

-0.54

 voulais

-0.53

 zatím

-0.52

SuppressLint

-0.52

cheinend

-0.51

IBOutlet

-0.50

Abp

-0.46

 dataSnapshot

-0.46

---*/

-0.46

дания

-0.45

POSITIVE LOGITS

 would

0.94

would

0.91

 WOULD

0.83

wouldn

0.77

 Would

0.74

Would

0.74

MigrationBuilder

0.72

msgTypes

0.72

 wouldn

0.70

GEBURTSDATUM

0.69

Activations Density 0.331%

phrases related to legality and ethical standards in behavior

No Comments

No Known Activations