INDEX

Explanations

programming language constructs and declarations, particularly focusing on method signatures and data types

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

 otomatig

-0.55

 currentState

-0.51

diyesi

-0.51

 currentValue

-0.51

 Hastings

-0.50

Referencer

-0.49

rafat

-0.49

 regaining

-0.48

TRAP

-0.47

 Shira

-0.46

POSITIVE LOGITS

set

0.82

 &___

0.70

 Wiktionnaire

0.69

set

0.65

enderror

0.56

原始内容存档于

0.55

Set

0.54

RefNanny

0.54

 sett

0.53

Set

0.53

Activations Density 0.030%

programming language constructs and declarations, particularly focusing on method signatures and data types

No Comments

No Known Activations