INDEX

Explanations

references to "this" or "these" along with their contextual usage

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

Followed by "this," "these," or "latter"

np_acts-logits-general · gemini-2.0-flash

this or these then 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

httphttps

-0.62

windowFixed

-0.61

 незавершена

-0.60

 ProtoMessage

-0.58

afficheront

-0.55

BibitemShut

-0.54

OGND

-0.54

NameInMap

-0.53

 wireType

-0.53

Abit

-0.52

POSITIVE LOGITS

 guys

0.38

 acest

0.38

 tohto

0.36

 productividad

0.36

 tästä

0.35

 chicos

0.35

こちらの

0.34

guy

0.33

 pauvreté

0.33

 Lingkungan

0.33

Activations Density 0.275%

references to "this" or "these" along with their contextual usage

Followed by "this," "these," or "latter"

this or these then noun

No Comments

No Known Activations