INDEX

Explanations

variations of the letter "W" and its associated usage in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

enumi

-0.80

 createSlice

-0.73

 nakalista

-0.70

 InputDecoration

-0.69

enumii

-0.69

 صوتيه

-0.69

getMenuInflater

-0.68

Casi

-0.67

 дописавши

-0.67

DialogComponent

-0.66

POSITIVE LOGITS

1.06

Waw

1.03

 Warriors

0.99

0.98

WS

0.95

WTS

0.95

wo

0.94

WAT

0.93

0.92

 Watson

0.92

Activations Density 1.914%

variations of the letter "W" and its associated usage in different contexts

No Comments

No Known Activations