INDEX

Explanations

references to specific legal terms and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

:✨

-0.60

 informée

-0.54

WriteBarrier

-0.50

 سكانية

-0.47

 otomatig

-0.47

HostException

-0.46

writeField

-0.46

 studia

-0.45

 Himo

-0.45

#+#

-0.44

POSITIVE LOGITS

ir

0.47

 createState

0.42

se

0.42

WindowConstants

0.39

 للاسماء

0.37

ese

0.36

AutoScaleMode

0.36

GroupLayout

0.36

RuleContext

0.36

ftagPool

0.36

Activations Density 0.105%

references to specific legal terms and citations

No Comments

No Known Activations