INDEX

Explanations

discussions about specific topics, particularly related to education and contributions within a community

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

 réguli

-0.71

 démocr

-0.68

 виправивши

-0.63

 Anſ

-0.62

 brancas

-0.59

 elettrica

-0.58

 flesta

-0.58

ReusableCell

-0.57

 normaux

-0.57

 tranquille

-0.56

POSITIVE LOGITS

how

1.60

why

1.43

如何

1.14

why

1.04

 whether

1.03

how

1.00

 what

1.00

 cómo

0.96

 possible

0.94

 warum

0.92

Activations Density 0.412%

discussions about specific topics, particularly related to education and contributions within a community

No Comments

No Known Activations