INDEX

Explanations

class and method definitions in programming code

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

<bos>

-0.53

 оригіналу

-0.48

ಿಕ

-0.47

tolsó

-0.45

 preval

-0.45

 nanti

-0.44

 Grail

-0.44

 alpina

-0.44

FWIW

-0.43

 señal

-0.42

POSITIVE LOGITS

ArgsConstructor

0.85

AndEndTag

0.80

 toString

0.71

ostream

0.65

addGap

0.62

 restTemplate

0.62

::~

0.61

migrationBuilder

0.60

hibernate

0.55

@[+][

0.55

Activations Density 0.213%

class and method definitions in programming code

No Comments

No Known Activations