INDEX

Explanations

language associated with medical or clinical implications, particularly in the context of surgery or treatment

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

followed by "to" or "of."

np_acts-logits-general · gemini-2.0-flash

state and relation descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

<h2>

-0.64

expandindo

-0.61

 Мексичка

-0.60

SOUNDBITE

-0.60

XmlAccessType

-0.58

发表于

-0.57

ligente

-0.57

andescent

-0.56

iredo

-0.56

antMatchers

-0.56

POSITIVE LOGITS

 thereto

0.61

WTS

0.60

 Unto

0.59

 unknownFields

0.58

 elástica

0.56

互联网档案馆

0.55

 kasarigan

0.55

AndView

0.55

__[

0.54

 تانيه

0.54

Activations Density 0.803%

language associated with medical or clinical implications, particularly in the context of surgery or treatment

followed by "to" or "of."

state and relation descriptors

No Comments

No Known Activations