INDEX

Explanations

functions and methods in code documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

↵↵

-0.70

<eos>

-0.56

mybatisplus

-0.55

oredCriteria

-0.51

<bos>

-0.49

basicConfig

-0.48

Personensuche

-0.47

 دیکھیے

-0.47

↵

-0.44

 kentang

-0.44

POSITIVE LOGITS

 للاسماء

0.89

 وتسجيلات

0.68

ſelves

0.66

ⓘ

0.65

Efq

0.65

tahui

0.63

 surla

0.63

Eſ

0.61

imarães

0.61

^(@)

0.61

Activations Density 0.047%

functions and methods in code documentation

No Comments

No Known Activations