INDEX

Explanations

references to semiconductor devices and digital signal processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

]--;

-0.68

aarrggbb

-0.67

 chinoise

-0.66

 chinois

-0.64

 Chinois

-0.61

GIVEREF

-0.60

TagMode

-0.60

 Wound

-0.59

Aiheesta

-0.58

contentLoaded

-0.58

POSITIVE LOGITS

tanleria

0.54

 nonatomic

0.54

AntiForgeryToken

0.52

leukin

0.51

 Reverso

0.45

flashdata

0.45

nocache

0.45

CHAFT

0.45

lético

0.43

وصلات

0.43

Activations Density 0.874%

references to semiconductor devices and digital signal processing

No Comments

No Known Activations