INDEX

Explanations

code snippets that refer to the Java programming language

oai_token-act-pair · gemini-2.0-flash

programming-related terms

np_token-act-pair-logits · gpt-4o-mini

java

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciclopedia

-0.59

ніципа

-0.53

 jsPsych

-0.53

NavController

-0.52

bindParam

-0.49

 Pristupljeno

-0.48

 Wikiquote

-0.48

 pantaloni

-0.48

 slik

-0.47

 roky

-0.47

POSITIVE LOGITS

OGND

0.76

RTEE

0.57

Autoritní

0.57

Personensuche

0.55

setVerticalGroup

0.52

}`).

0.49

UIControlState

0.47

 AssemblyProduct

0.46

ziu

0.46

glPushMatrix

0.45

Activations Density 0.519%

code snippets that refer to the Java programming language

programming-related terms

java

No Comments

No Known Activations