INDEX

Explanations

references to APIs and their documentation

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

wige

-0.54

IndentedString

-0.47

PLATES

-0.47

verwijspagina

-0.46

 professionali

-0.46

 smelt

-0.46

 charité

-0.45

 dAtA

-0.45

sibirsk

-0.44

 Lawler

-0.43

POSITIVE LOGITS

ViewImports

0.61

 XMLHttpRequest

0.61

 FileReader

0.60

expandindo

0.59

writeFieldEnd

0.58

 Pavlov

0.54

 photolibrary

0.54

LS

0.52

 getItemId

0.51

Maw

0.51

Activations Density 0.304%

references to APIs and their documentation

No Comments

No Known Activations