INDEX

Explanations

references to "research" and related terminology

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

"research"

np_acts-logits-general · gemini-2.0-flash

research

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

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

 ProtoMessage

-0.63

LookAnd

-0.57

 kaarangay

-0.52

 parachoque

-0.51

 nakalista

-0.49

цездатний

-0.48

 urusan

-0.45

 anún

-0.44

 réalis

-0.44

 AspNetCore

-0.44

POSITIVE LOGITS

 conducted

0.44

rch

0.44

erca

0.42

%)$

0.39

Gambas

0.39

 findings

0.38

forRoot

0.38

HostException

0.38

存于互联网档案馆

0.38

 project

0.36

Activations Density 0.054%

references to "research" and related terminology

"research"

research

No Comments

No Known Activations