INDEX

Explanations

descriptions of significant interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

>[]

-0.54

 متعلقه

-0.52

TypedDataSet

-0.50

 الدولى

-0.48

κλη

-0.46

isseurs

-0.45

udios

-0.45

intellij

-0.45

 فريبيس

-0.45

arean

-0.45

POSITIVE LOGITS

 Gait

0.78

trail

0.74

expandindo

0.68

一路

0.65

 stops

0.64

 Stops

0.64

reportWebVitals

0.62

 continuously

0.62

 TRAIL

0.61

 continuamente

0.60

Activations Density 0.296%

descriptions of significant interactions between characters

No Comments

No Known Activations