INDEX

Explanations

references to talent shows and their related elements

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

Gambas

-0.59

 akik

-0.57

 giornal

-0.54

 ktorí

-0.54

 wikipagina

-0.50

 vicina

-0.50

 maschile

-0.50

wives

-0.47

 normaux

-0.46

CodeAttribute

-0.45

POSITIVE LOGITS

 former

1.12

former

0.92

Former

0.92

 veteran

0.91

ex

0.89

 Former

0.87

这位

0.84

 singer

0.82

 Englishman

0.81

 Irishman

0.80

Activations Density 0.182%

references to talent shows and their related elements

No Comments

No Known Activations