INDEX

Explanations

elements related to programming and code documentation

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

Efq

-1.73

 Monfieur

-1.63

 Anſ

-1.63

 CHAPITRE

-1.63

 Houſe

-1.61

 iſt

-1.59

 Majefty

-1.59

 ―――――

-1.59

 Jefus

-1.57

 purpoſe

-1.56

POSITIVE LOGITS

kon

0.72

0.67

à

0.63

<eos>

0.61

nie

0.60

kan

0.60

les

0.60

le

0.58

Activations Density 1.601%

elements related to programming and code documentation

No Comments

No Known Activations