INDEX

Explanations

programming language syntax, particularly related to data structures and type definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

fromnode

-0.40

脚注の使い方

-0.39

protoimpl

-0.36

nloa

-0.35

 nahilalakip

-0.34

Commun

-0.33

tangentMode

-0.32

 atlik

-0.32

 Geschlecht

-0.31

 跳转至

-0.31

POSITIVE LOGITS

 setObject

0.68

 defaultdict

0.63

 getItemId

0.57

tanleria

0.53

ListItemIcon

0.53

awtextra

0.50

writeFieldEnd

0.49

colgroup

0.49

 Taktlose

0.48

PyExc

0.47

Activations Density 0.399%

programming language syntax, particularly related to data structures and type definitions

No Comments

No Known Activations