INDEX

Explanations

generic terms that relate to inclusivity and wide applicability

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

Followed by legal, moment, supported, of

np_acts-logits-general · gemini-2.0-flash

any followed by a noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Taktlose

-0.45

lapi

-0.40

+#+

-0.40

romolecules

-0.40

setdefault

-0.40

RefNanny

-0.40

 masking

-0.39

不清

-0.39

 indé

-0.39

Formazione

-0.38

POSITIVE LOGITS

 sofern

0.55

JspWriter

0.52

 reasonably

0.50

只要

0.50

reasonably

0.49

 unless

0.47

unless

0.46

 appropriately

0.45

 Wiktionnaire

0.45

 moderately

0.44

Activations Density 0.653%

generic terms that relate to inclusivity and wide applicability

Followed by legal, moment, supported, of

any followed by a noun

No Comments

No Known Activations