INDEX

Explanations

structured lists or organized information

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

 fós

-0.57

 링크

-0.48

 bakgrund

-0.48

Fuß

-0.48

 terza

-0.47

thea

-0.46

FTFY

-0.46

aza

-0.46

 consulté

-0.45

fflush

-0.45

POSITIVE LOGITS

IsContent

0.77

 Roskov

0.68

AutoScale

0.66

Geplaatst

0.64

 hObject

0.64

tagHelperRunner

0.62

errHandler

0.62

 незавершена

0.62

getDescriptor

0.59

 mxArray

0.58

Activations Density 0.165%

structured lists or organized information

No Comments

No Known Activations