INDEX

Explanations

definitions and mentions of lengths and dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

WebServlet

-0.56

 unanimous

-0.51

big

-0.49

Gos

-0.48

Rüyada

-0.47

Pas

-0.47

Protos

-0.47

big

-0.46

 ilman

-0.46

 Roskov

-0.45

POSITIVE LOGITS

length

0.86

 Length

0.86

ength

0.84

Length

0.83

 length

0.83

LENGTH

0.82

 lenght

0.71

getLength

0.67

 LENGTH

0.67

height

0.65

Activations Density 0.140%

definitions and mentions of lengths and dimensions

No Comments

No Known Activations