INDEX

Explanations

words related to power dynamics and clinical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

EndProject

-0.81

Datuak

-0.80

Vidite

-0.70

#+#

-0.68

GEBURTS

-0.66

sizeCache

-0.64

MigrationBuilder

-0.64

клопе

-0.62

sidemargin

-0.61

EndGlobalSection

-0.61

POSITIVE LOGITS

 chiếu

0.58

لينا

0.53

 prochaines

0.49

 동안

0.49

 antaranya

0.48

おわりに

0.48

breos

0.48

Redaktion

0.47

Says

0.47

 Valent

0.47

Activations Density 1.296%

words related to power dynamics and clinical contexts

No Comments

No Known Activations