INDEX

Explanations

punctuations and sentence boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 intptr

-0.70

initState

-0.68

WriteBarrier

-0.59

љено

-0.58

awtextra

-0.56

tagHelperRunner

-0.55

 TextInputType

-0.55

amse

-0.54

ioutil

-0.53

OrNil

-0.52

POSITIVE LOGITS

 للمعارف

0.95

 nakalista

0.79

 apologised

0.57

 stabilisation

0.54

isation

0.53

 scepticism

0.52

 emphasised

0.50

 maximise

0.49

"(

0.48

 apologise

0.48

Activations Density 0.056%

punctuations and sentence boundaries

No Comments

No Known Activations