INDEX

Explanations

tech-related terminology, especially around data structures and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Adam

-0.51

enterOuterAlt

-0.47

Adam

-0.44

<eos>

-0.43

od

-0.41

mo

-0.41

door

-0.40

ru

-0.39

(**

-0.38

 मु

-0.38

POSITIVE LOGITS

 array

2.06

 Array

1.89

array

1.73

 arrays

1.68

Array

1.67

 ARRAY

1.65

数组

1.54

ARRAY

1.50

 Arrays

1.50

arr

1.44

Activations Density 0.402%

tech-related terminology, especially around data structures and programming concepts

No Comments

No Known Activations