INDEX

Explanations

keywords or tokens related to computational or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

RegistryLite

-0.53

setVerticalGroup

-0.50

har

-0.49

Filmographie

-0.48

short

-0.45

[]

-0.44

ِّف

-0.44

reggio

-0.42

 used

-0.42

rey

-0.41

POSITIVE LOGITS

posedge

0.68

:✨

0.66

HasIndex

0.66

Билгалдахарш

0.64

 isNameExpr

0.63

 picioare

0.63

 ricordi

0.61

mybatisplus

0.60

 fourrure

0.60

 biografias

0.59

Activations Density 0.163%

keywords or tokens related to computational or programming contexts

No Comments

No Known Activations