INDEX

Explanations

technical terms related to execution 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 @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

bpy

-0.45

 daly

-0.43

Mutex

-0.43

#+#

-0.43

 mourut

-0.42

ynb

-0.42

SPATH

-0.41

walt

-0.41

yszer

-0.40

spli

-0.40

POSITIVE LOGITS

GEBURTSDATUM

0.76

 BoxFit

0.75

ⓧ

0.69

 kaynağından

0.69

ftagPool

0.69

 NSCoder

0.68

StoryboardSegue

0.68

FormTagHelper

0.67

:✨

0.63

aarrggbb

0.62

Activations Density 0.829%

technical terms related to execution and programming concepts

No Comments

No Known Activations