INDEX

Explanations

code import statements and component definitions

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

 Majesté

-0.56

ynchronously

-0.55

 industrielle

-0.53

ostante

-0.52

œurs

-0.50

 zewnętrzne

-0.50

 Infórmanos

-0.49

 tuyo

-0.48

cillors

-0.47

 normaux

-0.46

POSITIVE LOGITS

Datuak

0.77

GeneratedValue

0.69

=[]

0.63

=[

0.63

DebuggerNonUser

0.60

Gweler

0.59

 AssemblyProduct

0.59

GenerationType

0.58

=>'

0.58

))){

0.58

Activations Density 0.071%

code import statements and component definitions

No Comments

No Known Activations